Local LLM · GGUF
Best local GGUF models for your GPU
Pick your host platform first. Macs use MLX (LM Studio / mlx-lm). PCs and Spark boxes use GGUF in Ollama, LM Studio, or llama.cpp. Then choose the job and how much memory you have. Sized from ollama.com/library.
Works with: Ollama · LM Studio · llama.cpp
x86_64 (PC) — Windows / Linux · GGUF · CUDA / ROCm / Vulkan. Typical desktop or workstation with a discrete GPU. GGUF models run in Ollama, LM Studio, or llama.cpp.
Clear winner · Build · x86_64 (PC) · ≤24 GB
#1north-mini-code-1.0 123B123B · ~21 GB · fit 88
ollama pull north-mini-code-1.0:123b- #2north-mini-code-1.0 120Bfit 88 · 120B
ollama pull north-mini-code-1.0:120b - #3north-mini-code-1.0 119Bfit 87 · 119B
ollama pull north-mini-code-1.0:119b - #4north-mini-code-1.0 35Bfit 69 · 35B
ollama pull north-mini-code-1.0:35b - #5codebooga 34Bfit 68 · 34B
ollama pull codebooga:34b - #6codellama 34Bfit 68 · 34B
ollama pull codellama:34b
How fit works
- Plan / Research / Build — parameter scale is the main signal. A ~120B model outranks a 3–4B “reasoner” tag; family names are only a nudge.
- Chat — prefers mid-small everyday sizes (~3–14B). Huge models are overkill.
- Create — vision / image models only; size ranks within that set.
- Fit — uncapped raw score (can go past 100). Highest in your host + memory filter is the clear #1 winner.
- Hosts: x86 + Spark → GGUF for Ollama / LM Studio / llama.cpp; Mac → MLX for LM Studio / mlx-lm. Switching platform swaps the whole model list.
334 models · Build · x86_64 (PC)
| Model id | ||||||
|---|---|---|---|---|---|---|
#1north-mini-code-1.0 123B Ollama library | Build | 88 | x86 · Spark | 123B | ~21 GB | north-mini-code-1.0:123b |
north-mini-code-1.0 120B Ollama library | Build | 88#2 | x86 · Spark | 120B | ~21 GB | north-mini-code-1.0:120b |
north-mini-code-1.0 119B Ollama library | Build | 87#3 | x86 · Spark | 119B | ~21 GB | north-mini-code-1.0:119b |
north-mini-code-1.0 35B Ollama library | Build | 69#4 | x86 · Spark | 35B | ~21 GB | north-mini-code-1.0:35b |
codebooga 34B Ollama library | Build | 68#5 | x86 · Spark | 34B | ~21 GB | codebooga:34b |
codellama 34B Meta | Build | 68#6 | x86 · Spark | 34B | ~21 GB | codellama:34b |
granite-code 34B IBM | Build | 68#7 | x86 · Spark | 34B | ~21 GB | granite-code:34b |
llava 34B Ollama library | Create | 68#8 | x86 · Spark | 34B | ~21 GB | llava:34b |
phind-codellama 34B Microsoft | Build | 68#9 | x86 · Spark | 34B | ~21 GB | phind-codellama:34b |
deepseek-coder 33B DeepSeek | Build | 68#10 | x86 · Spark | 33B | ~21 GB | deepseek-coder:33b |
wizardcoder 33B Ollama library | Build | 68#11 | x86 · Spark | 33B | ~21 GB | wizardcoder:33b |
qwen2.5-coder 32B Alibaba | Chat | 67#12 | x86 · Spark | 32B | ~20 GB | qwen2.5-coder:32b |
north-mini-code-1.0 30B Ollama library | Chat | 66#13 | x86 · Spark | 30B | ~21 GB | north-mini-code-1.0:30b |
qwen3-coder 30B Alibaba | Chat | 66#14 | x86 · Spark | 30B | ~19 GB | qwen3-coder:30b |
north-mini-code-1.0 26B Ollama library | Chat | 65#15 | x86 · Spark | 26B | ~21 GB | north-mini-code-1.0:26b |
devstral 24B Mistral | Chat | 64#16 | x86 · Spark | 24B | ~16 GB | devstral:24b |
devstral-small-2 24B Mistral | Chat | 64#17 | x86 · Spark | 24B | ~16 GB | devstral-small-2:24b |
north-mini-code-1.0 24B Ollama library | Chat | 64#18 | x86 · Spark | 24B | ~21 GB | north-mini-code-1.0:24b |
codestral 22B Mistral | Chat | 62#19 | x86 · Spark | 22B | ~15 GB | codestral:22b |
granite-code 20B IBM | Chat | 61#20 | x86 · Spark | 20B | ~13 GB | granite-code:20b |
deepseek-coder-v2 16B DeepSeek | Chat | 58#21 | x86 · Spark | 16B | ~11 GB | deepseek-coder-v2:16b |
dolphincoder 15B Ollama library | Chat | 58#22 | x86 · Spark | 15B | ~11 GB | dolphincoder:15b |
sqlcoder 15B Ollama library | Chat | 58#23 | x86 · Spark | 15B | ~11 GB | sqlcoder:15b |
starcoder 15B Ollama library | Chat | 58#24 | x86 · Spark | 15B | ~11 GB | starcoder:15b |
starcoder2 15B Ollama library | Chat | 58#25 | x86 · Spark | 15B | ~11 GB | starcoder2:15b |
alfred 40B Ollama library | Chat | 57#26 | x86 · Spark | 40B | ~24 GB | alfred:40b |
deepcoder 14B Ollama library | Chat | 57#27 | x86 · Spark | 14B | ~10 GB | deepcoder:14b |
qwen2.5-coder 14B Alibaba | Chat | 57#28 | x86 · Spark | 14B | ~10 GB | qwen2.5-coder:14b |
nemotron3 33B NVIDIA | Create | 56#29 | x86 · Spark | 33B | ~21 GB | nemotron3:33b |
codellama 13B Meta | Chat | 56#30 | x86 · Spark | 13B | ~10 GB | codellama:13b |
codeup 13B Ollama library | Chat | 56#31 | x86 · Spark | 13B | ~10 GB | codeup:13b |
llava 13B Ollama library | Chat | 56#32 | x86 · Spark | 13B | ~10 GB | llava:13b |
open-orca-platypus2 13B Ollama library | Chat | 56#33 | x86 · Spark | 13B | ~10 GB | open-orca-platypus2:13b |
command-r 35B Cohere | Plan | 55#34 | x86 · Spark | 35B | ~22 GB | command-r:35b |
qwen3.5 35B Alibaba | Plan | 55#35 | x86 · Spark | 35B | ~22 GB | qwen3.5:35b |
qwen3.6 35B Alibaba | Plan | 55#36 | x86 · Spark | 35B | ~22 GB | qwen3.6:35b |
nemotron-3-nano 30B NVIDIA | Chat | 55#37 | x86 · Spark | 30B | ~19 GB | nemotron-3-nano:30b |
nemotron-cascade-2 30B NVIDIA | Chat | 55#38 | x86 · Spark | 30B | ~19 GB | nemotron-cascade-2:30b |
cogito 32B Ollama library | Chat | 54#39 | x86 · Spark | 32B | ~20 GB | cogito:32b |
exaone3.5 32B Ollama library | Chat | 54#40 | x86 · Spark | 32B | ~20 GB | exaone3.5:32b |
qwen 32B Alibaba | Chat | 54#41 | x86 · Spark | 32B | ~20 GB | qwen:32b |
qwen2.5 32B Alibaba | Chat | 54#42 | x86 · Spark | 32B | ~20 GB | qwen2.5:32b |
qwen2.5vl 32B Alibaba | Chat | 54#43 | x86 · Spark | 32B | ~20 GB | qwen2.5vl:32b |
qwen3 32B Alibaba | Chat | 54#44 | x86 · Spark | 32B | ~20 GB | qwen3:32b |
qwen3-vl 32B Alibaba | Create | 54#45 | x86 · Spark | 32B | ~20 GB | qwen3-vl:32b |
qwq 32B Alibaba | Chat | 54#46 | x86 · Spark | 32B | ~20 GB | qwq:32b |
falcon2 11B TII | Chat | 54#47 | x86 · Spark | 11B | ~9 GB | falcon2:11b |
gemma4 31B Google | Chat | 53#48 | x86 · Spark | 31B | ~20 GB | gemma4:31b |
qwen3 30B Alibaba | Chat | 53#49 | x86 · Spark | 30B | ~19 GB | qwen3:30b |
qwen3-vl 30B Alibaba | Create | 53#50 | x86 · Spark | 30B | ~19 GB | qwen3-vl:30b |
codegeex4 9B Zhipu | Chat | 52#51 | x86 · Spark | 9B | ~7 GB | codegeex4:9b |
yi-coder 9B 01.AI | Chat | 52#52 | x86 · Spark | 9B | ~7 GB | yi-coder:9b |
falcon 40B TII | Chat | 51#53 | x86 · Spark | 40B | ~24 GB | falcon:40b |
gemma2 27B Google | Chat | 51#54 | x86 · Spark | 27B | ~17 GB | gemma2:27b |
gemma3 27B Google | Chat | 51#55 | x86 · Spark | 27B | ~17 GB | gemma3:27b |
medgemma 27B Ollama library | Chat | 51#56 | x86 · Spark | 27B | ~17 GB | medgemma:27b |
qwen3.5 27B Alibaba | Chat | 51#57 | x86 · Spark | 27B | ~17 GB | qwen3.5:27b |
qwen3.6 27B Alibaba | Chat | 51#58 | x86 · Spark | 27B | ~17 GB | qwen3.6:27b |
shieldgemma 27B Ollama library | Chat | 51#59 | x86 · Spark | 27B | ~17 GB | shieldgemma:27b |
translategemma 27B Ollama library | Chat | 51#60 | x86 · Spark | 27B | ~17 GB | translategemma:27b |
gemma4 26B Google | Chat | 51#61 | x86 · Spark | 26B | ~17 GB | gemma4:26b |
granite-code 8B IBM | Chat | 51#62 | x86 · Spark | 8B | ~7 GB | granite-code:8b |
granite3-dense 8B IBM | Chat | 51#63 | x86 · Spark | 8B | ~7 GB | granite3-dense:8b |
opencoder 8B Ollama library | Chat | 51#64 | x86 · Spark | 8B | ~7 GB | opencoder:8b |
rnj-1 8B Ollama library | Chat | 51#65 | x86 · Spark | 8B | ~7 GB | rnj-1:8b |
tulu3 8B Ollama library | Chat | 51#66 | x86 · Spark | 8B | ~7 GB | tulu3:8b |
mistral-small 24B Mistral | Chat | 50#67 | x86 · Spark | 24B | ~16 GB | mistral-small:24b |
mistral-small3.1 24B Mistral | Create | 50#68 | x86 · Spark | 24B | ~16 GB | mistral-small3.1:24b |
mistral-small3.2 24B Mistral | Chat | 50#69 | x86 · Spark | 24B | ~16 GB | mistral-small3.2:24b |
codegemma 7B Google | Chat | 50#70 | x86 · Spark | 7B | ~6 GB | codegemma:7b |
codellama 7B Meta | Chat | 50#71 | x86 · Spark | 7B | ~6 GB | codellama:7b |
codeqwen 7B Alibaba | Chat | 50#72 | x86 · Spark | 7B | ~6 GB | codeqwen:7b |
dolphincoder 7B Ollama library | Chat | 50#73 | x86 · Spark | 7B | ~6 GB | dolphincoder:7b |
llava 7B Ollama library | Chat | 50#74 | x86 · Spark | 7B | ~6 GB | llava:7b |
magicoder 7B Ollama library | Chat | 50#75 | x86 · Spark | 7B | ~6 GB | magicoder:7b |
qwen2.5-coder 7B Alibaba | Chat | 50#76 | x86 · Spark | 7B | ~6 GB | qwen2.5-coder:7b |
sqlcoder 7B Ollama library | Chat | 50#77 | x86 · Spark | 7B | ~6 GB | sqlcoder:7b |
starcoder 7B Ollama library | Chat | 50#78 | x86 · Spark | 7B | ~6 GB | starcoder:7b |
starcoder2 7B Ollama library | Chat | 50#79 | x86 · Spark | 7B | ~6 GB | starcoder2:7b |
aya 35B Ollama library | Chat | 49#80 | x86 · Spark | 35B | ~22 GB | aya:35b |
ornith 35B Ollama library | Chat | 49#81 | x86 · Spark | 35B | ~22 GB | ornith:35b |
mistral-small 22B Mistral | Chat | 49#82 | x86 · Spark | 22B | ~15 GB | mistral-small:22b |
gpt-oss 20B OpenAI (open weights) | Chat | 49#83 | x86 · Spark | 20B | ~13 GB | gpt-oss:20b |
gpt-oss-safeguard 20B OpenAI (open weights) | Chat | 49#84 | x86 · Spark | 20B | ~13 GB | gpt-oss-safeguard:20b |
deepseek-coder 6.7B DeepSeek | Chat | 49#85 | x86 · Spark | 6.7B | ~6 GB | deepseek-coder:6.7b |
nous-hermes2 34B Ollama library | Chat | 48#86 | x86 · Spark | 34B | ~21 GB | nous-hermes2:34b |
yi 34B 01.AI | Chat | 48#87 | x86 · Spark | 34B | ~21 GB | yi:34b |
vicuna 33B Ollama library | Chat | 48#88 | x86 · Spark | 33B | ~21 GB | vicuna:33b |
aya-expanse 32B Ollama library | Chat | 47#89 | x86 · Spark | 32B | ~20 GB | aya-expanse:32b |
deepseek-r1 32B DeepSeek | Chat | 47#90 | x86 · Spark | 32B | ~20 GB | deepseek-r1:32b |
exaone-deep 32B Ollama library | Chat | 47#91 | x86 · Spark | 32B | ~20 GB | exaone-deep:32b |
olmo-3 32B Ollama library | Chat | 47#92 | x86 · Spark | 32B | ~20 GB | olmo-3:32b |
olmo-3.1 32B Ollama library | Chat | 47#93 | x86 · Spark | 32B | ~20 GB | olmo-3.1:32b |
openthinker 32B Ollama library | Chat | 47#94 | x86 · Spark | 32B | ~20 GB | openthinker:32b |
glm-4.7-flash 30B Zhipu | Chat | 46#95 | x86 · Spark | 30B | ~21 GB | glm-4.7-flash:30b |
granite4.1 30B IBM | Chat | 46#96 | x86 · Spark | 30B | ~19 GB | granite4.1:30b |
wizard-vicuna-uncensored 30B Ollama library | Chat | 46#97 | x86 · Spark | 30B | ~19 GB | wizard-vicuna-uncensored:30b |
wizardlm 30B Ollama library | Chat | 46#98 | x86 · Spark | 30B | ~19 GB | wizardlm:30b-q4_K_M |
magistral 24B Ollama library | Chat | 44#99 | x86 · Spark | 24B | ~16 GB | magistral:24b |
cogito 14B Ollama library | Chat | 43#100 | x86 · Spark | 14B | ~10 GB | cogito:14b |
phi3 14B Microsoft | Chat | 43#101 | x86 · Spark | 14B | ~10 GB | phi3:14b |
phi4 14B Microsoft | Chat | 43#102 | x86 · Spark | 14B | ~10 GB | phi4:14b |
phi4-reasoning 14B Microsoft | Chat | 43#103 | x86 · Spark | 14B | ~10 GB | phi4-reasoning:14b |
qwen 14B Alibaba | Chat | 43#104 | x86 · Spark | 14B | ~10 GB | qwen:14b |
qwen2.5 14B Alibaba | Chat | 43#105 | x86 · Spark | 14B | ~10 GB | qwen2.5:14b |
qwen3 14B Alibaba | Chat | 43#106 | x86 · Spark | 14B | ~10 GB | qwen3:14b |
mistral-nemo 12B Mistral | Chat | 43#107 | x86 · Spark | 12B | ~9 GB | mistral-nemo:12b |
solar-pro 22B Ollama library | Chat | 42#108 | x86 · Spark | 22B | ~15 GB | solar-pro:22b |
nexusraven 13B Ollama library | Chat | 42#109 | x86 · Spark | 13B | ~10 GB | nexusraven:13b |
granite-code 3B IBM | Chat | 42#110 | x86 · Spark | 3B | ~4 GB | granite-code:3b |
north-mini-code-1.0 3B Ollama library | Chat | 42#111 | x86 · Spark | 3B | ~21 GB | north-mini-code-1.0:3b |
qwen2.5-coder 3B Alibaba | Chat | 42#112 | x86 · Spark | 3B | ~4 GB | qwen2.5-coder:3b |
stable-code 3B Ollama library | Chat | 42#113 | x86 · Spark | 3B | ~4 GB | stable-code:3b |
starcoder 3B Ollama library | Chat | 42#114 | x86 · Spark | 3B | ~4 GB | starcoder:3b |
starcoder2 3B Ollama library | Chat | 42#115 | x86 · Spark | 3B | ~4 GB | starcoder2:3b |
glm-4.7-flash 20B Zhipu | Chat | 41#116 | x86 · Spark | 20B | ~21 GB | glm-4.7-flash:20b |
internlm2 20B Ollama library | Chat | 41#117 | x86 · Spark | 20B | ~13 GB | internlm2:20b |
sailor2 20B Ollama library | Chat | 41#118 | x86 · Spark | 20B | ~13 GB | sailor2:20b |
gemma3 12B Google | Chat | 41#119 | x86 · Spark | 12B | ~9 GB | gemma3:12b |
gemma4 12B Google | Chat | 41#120 | x86 · Spark | 12B | ~9 GB | gemma4:12b |
translategemma 12B Ollama library | Chat | 41#121 | x86 · Spark | 12B | ~9 GB | translategemma:12b |
llama3.2-vision 11B Meta | Chat | 40#122 | x86 · Spark | 11B | ~9 GB | llama3.2-vision:11b |
codegemma 2B Google | Chat | 40#123 | x86 · Spark | 2B | ~4 GB | codegemma:2b |
granite3-dense 2B IBM | Chat | 40#124 | x86 · Spark | 2B | ~4 GB | granite3-dense:2b |
llama4 17B Meta | Chat | 39#125 | x86 · Spark | 17B | ~12 GB | llama4:17b |
llama3-chatqa 8B Meta | Chat | 39#126 | x86 · Spark | 8B | ~7 GB | llama3-chatqa:8b |
deepseek-v2 16B DeepSeek | Chat | 38#127 | x86 · Spark | 16B | ~11 GB | deepseek-v2:16b |
gemma2 9B Google | Chat | 38#128 | x86 · Spark | 9B | ~7 GB | gemma2:9b |
qwen3.5 9B Alibaba | Chat | 38#129 | x86 · Spark | 9B | ~7 GB | qwen3.5:9b |
shieldgemma 9B Ollama library | Chat | 38#130 | x86 · Spark | 9B | ~7 GB | shieldgemma:9b |
deepcoder 1.5B Ollama library | Chat | 38#131 | x86 · Spark | 1.5B | ~3 GB | deepcoder:1.5b |
opencoder 1.5B Ollama library | Chat | 38#132 | x86 · Spark | 1.5B | ~3 GB | opencoder:1.5b |
qwen2.5-coder 1.5B Alibaba | Chat | 38#133 | x86 · Spark | 1.5B | ~3 GB | qwen2.5-coder:1.5b |
yi-coder 1.5B 01.AI | Chat | 38#134 | x86 · Spark | 1.5B | ~3 GB | yi-coder:1.5b |
deepseek-r1 14B DeepSeek | Chat | 37#135 | x86 · Spark | 14B | ~10 GB | deepseek-r1:14b |
ministral-3 14B Mistral | Chat | 37#136 | x86 · Spark | 14B | ~10 GB | ministral-3:14b |
cogito 8B Ollama library | Chat | 37#137 | x86 · Spark | 8B | ~7 GB | cogito:8b |
dolphin-llama3 8B Ollama library | Chat | 37#138 | x86 · Spark | 8B | ~7 GB | dolphin-llama3:8b |
dolphin3 8B Ollama library | Chat | 37#139 | x86 · Spark | 8B | ~7 GB | dolphin3:8b |
granite3.3 8B IBM | Chat | 37#140 | x86 · Spark | 8B | ~7 GB | granite3.3:8b |
llama-pro 8B Meta | Chat | 37#141 | x86 · Spark | 8B | ~7 GB | llama-pro:8b-instruct-q4_K_M |
llama3 8B Meta | Chat | 37#142 | x86 · Spark | 8B | ~7 GB | llama3:8b |
llama3-gradient 8B Meta | Chat | 37#143 | x86 · Spark | 8B | ~7 GB | llama3-gradient:8b |
llama3-groq-tool-use 8B Meta | Chat | 37#144 | x86 · Spark | 8B | ~7 GB | llama3-groq-tool-use:8b |
llama3.1 8B Meta | Chat | 37#145 | x86 · Spark | 8B | ~7 GB | llama3.1:8b |
llava-llama3 8B Ollama library | Chat | 37#146 | x86 · Spark | 8B | ~7 GB | llava-llama3:8b |
qwen3 8B Alibaba | Chat | 37#147 | x86 · Spark | 8B | ~7 GB | qwen3:8b |
qwen3-vl 8B Alibaba | Chat | 37#148 | x86 · Spark | 8B | ~7 GB | qwen3-vl:8b |
exaone3.5 7.8B Ollama library | Chat | 37#149 | x86 · Spark | 7.8B | ~7 GB | exaone3.5:7.8b |
deepseek-coder 1.3B DeepSeek | Chat | 37#150 | x86 · Spark | 1.3B | ~3 GB | deepseek-coder:1.3b |
everythinglm 13B Ollama library | Chat | 36#151 | x86 · Spark | 13B | ~10 GB | everythinglm:13b |
llama2 13B Meta | Chat | 36#152 | x86 · Spark | 13B | ~10 GB | llama2:13b |
llama2-chinese 13B Meta | Chat | 36#153 | x86 · Spark | 13B | ~10 GB | llama2-chinese:13b |
nous-hermes 13B Ollama library | Chat | 36#154 | x86 · Spark | 13B | ~10 GB | nous-hermes:13b |
olmo2 13B Ollama library | Chat | 36#155 | x86 · Spark | 13B | ~10 GB | olmo2:13b |
orca-mini 13B Ollama library | Chat | 36#156 | x86 · Spark | 13B | ~10 GB | orca-mini:13b |
orca2 13B Ollama library | Chat | 36#157 | x86 · Spark | 13B | ~10 GB | orca2:13b |
stable-beluga 13B Ollama library | Chat | 36#158 | x86 · Spark | 13B | ~10 GB | stable-beluga:13b |
vicuna 13B Ollama library | Chat | 36#159 | x86 · Spark | 13B | ~10 GB | vicuna:13b |
wizard-math 13B Ollama library | Chat | 36#160 | x86 · Spark | 13B | ~10 GB | wizard-math:13b |
wizard-vicuna 13B Ollama library | Chat | 36#161 | x86 · Spark | 13B | ~10 GB | wizard-vicuna:13b |
wizard-vicuna-uncensored 13B Ollama library | Chat | 36#162 | x86 · Spark | 13B | ~10 GB | wizard-vicuna-uncensored:13b |
wizardlm 13B Ollama library | Chat | 36#163 | x86 · Spark | 13B | ~10 GB | wizardlm:13b-llama2-q4_K_M |
wizardlm-uncensored 13B Ollama library | Chat | 36#164 | x86 · Spark | 13B | ~10 GB | wizardlm-uncensored:13b |
xwinlm 13B Ollama library | Chat | 36#165 | x86 · Spark | 13B | ~10 GB | xwinlm:13b |
yarn-llama2 13B Ollama library | Chat | 36#166 | x86 · Spark | 13B | ~10 GB | yarn-llama2:13b |
bakllava 7B Ollama library | Chat | 36#167 | x86 · Spark | 7B | ~6 GB | bakllava:7b |
command-r7b 7B Cohere | Chat | 36#168 | x86 · Spark | 7B | ~6 GB | command-r7b:7b |
command-r7b-arabic 7B Cohere | Chat | 36#169 | x86 · Spark | 7B | ~6 GB | command-r7b-arabic:7b |
dolphin-mistral 7B Ollama library | Chat | 36#170 | x86 · Spark | 7B | ~6 GB | dolphin-mistral:7b |
dolphin-mixtral 7B Ollama library | Chat | 36#171 | x86 · Spark | 7B | ~6 GB | dolphin-mixtral |
gemma 7B Google | Chat | 36#172 | x86 · Spark | 7B | ~6 GB | gemma:7b |
mathstral 7B Ollama library | Chat | 36#173 | x86 · Spark | 7B | ~6 GB | mathstral:7b |
mistral 7B Mistral | Chat | 36#174 | x86 · Spark | 7B | ~6 GB | mistral:7b |
mistral-openorca 7B Mistral | Chat | 36#175 | x86 · Spark | 7B | ~6 GB | mistral-openorca:7b |
mistrallite 7B Mistral | Chat | 36#176 | x86 · Spark | 7B | ~6 GB | mistrallite:7b |
neural-chat 7B Ollama library | Chat | 36#177 | x86 · Spark | 7B | ~6 GB | neural-chat:7b |
openhermes 7B Ollama library | Chat | 36#178 | x86 · Spark | 7B | ~6 GB | openhermes:7b-mistral-v2-q4_K_M |
qwen 7B Alibaba | Chat | 36#179 | x86 · Spark | 7B | ~6 GB | qwen:7b |
qwen2 7B Alibaba | Chat | 36#180 | x86 · Spark | 7B | ~6 GB | qwen2:7b |
qwen2-math 7B Alibaba | Chat | 36#181 | x86 · Spark | 7B | ~6 GB | qwen2-math:7b |
qwen2.5 7B Alibaba | Chat | 36#182 | x86 · Spark | 7B | ~6 GB | qwen2.5:7b |
qwen2.5vl 7B Alibaba | Chat | 36#183 | x86 · Spark | 7B | ~6 GB | qwen2.5vl:7b |
samantha-mistral 7B Ollama library | Chat | 36#184 | x86 · Spark | 7B | ~6 GB | samantha-mistral:7b |
yarn-mistral 7B Ollama library | Chat | 36#185 | x86 · Spark | 7B | ~6 GB | yarn-mistral:7b |
zephyr 7B Ollama library | Chat | 36#186 | x86 · Spark | 7B | ~6 GB | zephyr:7b |
starcoder 1B Ollama library | Chat | 36#187 | x86 · Spark | 1B | ~3 GB | starcoder:1b |
stablelm2 12B Ollama library | Chat | 35#188 | x86 · Spark | 12B | ~9 GB | stablelm2:12b |
glm-ocr 0.9B Zhipu | Chat | 35#189 | x86 · Spark | 900M | ~5 GB | glm-ocr:0.9b |
nous-hermes2 10.7B Ollama library | Chat | 34#190 | x86 · Spark | 10.7B | ~8 GB | nous-hermes2:10.7b |
solar 10.7B Ollama library | Chat | 34#191 | x86 · Spark | 10.7B | ~8 GB | solar:10.7b |
falcon3 10B TII | Chat | 33#192 | x86 · Spark | 10B | ~8 GB | falcon3:10b |
nemotron-3-nano 4B NVIDIA | Chat | 33#193 | x86 · Spark | 4B | ~5 GB | nemotron-3-nano:4b |
nemotron-mini 4B NVIDIA | Chat | 33#194 | x86 · Spark | 4B | ~5 GB | nemotron-mini:4b |
glm-ocr 0.5B Zhipu | Chat | 33#195 | x86 · Spark | 500M | ~5 GB | glm-ocr:0.5b |
qwen2.5-coder 0.5B Alibaba | Chat | 33#196 | x86 · Spark | 500M | ~3 GB | qwen2.5-coder:0.5b |
glm4 9B Zhipu | Chat | 32#197 | x86 · Spark | 9B | ~7 GB | glm4:9b |
ornith 9B Ollama library | Chat | 32#198 | x86 · Spark | 9B | ~7 GB | ornith:9b |
yi 9B 01.AI | Chat | 32#199 | x86 · Spark | 9B | ~7 GB | yi:9b |
aya 8B Ollama library | Chat | 31#200 | x86 · Spark | 8B | ~7 GB | aya:8b |
aya-expanse 8B Ollama library | Chat | 31#201 | x86 · Spark | 8B | ~7 GB | aya-expanse:8b |
deepseek-r1 8B DeepSeek | Chat | 31#202 | x86 · Spark | 8B | ~7 GB | deepseek-r1:8b |
granite3-guardian 8B IBM | Chat | 31#203 | x86 · Spark | 8B | ~7 GB | granite3-guardian:8b |
granite3.1-dense 8B IBM | Chat | 31#204 | x86 · Spark | 8B | ~7 GB | granite3.1-dense:8b |
granite3.2 8B IBM | Chat | 31#205 | x86 · Spark | 8B | ~7 GB | granite3.2:8b |
granite4.1 8B IBM | Chat | 31#206 | x86 · Spark | 8B | ~7 GB | granite4.1:8b |
granite4.1-guardian 8B IBM | Chat | 31#207 | x86 · Spark | 8B | ~7 GB | granite4.1-guardian:8b |
hermes3 8B Ollama library | Chat | 31#208 | x86 · Spark | 8B | ~7 GB | hermes3:8b |
llama-guard3 8B Meta | Chat | 31#209 | x86 · Spark | 8B | ~7 GB | llama-guard3:8b |
minicpm-v 8B Ollama library | Chat | 31#210 | x86 · Spark | 8B | ~7 GB | minicpm-v:8b |
minicpm-v4.5 8B Ollama library | Chat | 31#211 | x86 · Spark | 8B | ~7 GB | minicpm-v4.5:8b |
ministral-3 8B Mistral | Chat | 31#212 | x86 · Spark | 8B | ~7 GB | ministral-3:8b |
sailor2 8B Ollama library | Chat | 31#213 | x86 · Spark | 8B | ~7 GB | sailor2:8b |
exaone-deep 7.8B Ollama library | Chat | 31#214 | x86 · Spark | 7.8B | ~7 GB | exaone-deep:7.8b |
gemma3 4B Google | Chat | 31#215 | x86 · Spark | 4B | ~5 GB | gemma3:4b |
gemma3n 4B Google | Chat | 31#216 | x86 · Spark | 4B | ~5 GB | gemma3n:4b |
medgemma 4B Ollama library | Chat | 31#217 | x86 · Spark | 4B | ~5 GB | medgemma:4b |
medgemma1.5 4B Ollama library | Chat | 31#218 | x86 · Spark | 4B | ~5 GB | medgemma1.5:4b |
qwen 4B Alibaba | Chat | 31#219 | x86 · Spark | 4B | ~5 GB | qwen:4b |
qwen3 4B Alibaba | Chat | 31#220 | x86 · Spark | 4B | ~5 GB | qwen3:4b |
qwen3-vl 4B Alibaba | Chat | 31#221 | x86 · Spark | 4B | ~5 GB | qwen3-vl:4b |
qwen3.5 4B Alibaba | Chat | 31#222 | x86 · Spark | 4B | ~5 GB | qwen3.5:4b |
translategemma 4B Ollama library | Chat | 31#223 | x86 · Spark | 4B | ~5 GB | translategemma:4b |
bespoke-minicheck 7B Ollama library | Chat | 30#224 | x86 · Spark | 7B | ~6 GB | bespoke-minicheck:7b |
deepseek-llm 7B DeepSeek | Chat | 30#225 | x86 · Spark | 7B | ~6 GB | deepseek-llm:7b |
deepseek-r1 7B DeepSeek | Chat | 30#226 | x86 · Spark | 7B | ~6 GB | deepseek-r1:7b |
duckdb-nsql 7B Ollama library | Chat | 30#227 | x86 · Spark | 7B | ~6 GB | duckdb-nsql:7b |
falcon 7B TII | Chat | 30#228 | x86 · Spark | 7B | ~6 GB | falcon:7b |
falcon3 7B TII | Chat | 30#229 | x86 · Spark | 7B | ~6 GB | falcon3:7b |
internlm2 7B Ollama library | Chat | 30#230 | x86 · Spark | 7B | ~6 GB | internlm2:7b |
llama2 7B Meta | Chat | 30#231 | x86 · Spark | 7B | ~6 GB | llama2:7b |
llama2-chinese 7B Meta | Chat | 30#232 | x86 · Spark | 7B | ~6 GB | llama2-chinese:7b |
llama2-uncensored 7B Meta | Chat | 30#233 | x86 · Spark | 7B | ~6 GB | llama2-uncensored:7b |
marco-o1 7B Ollama library | Chat | 30#234 | x86 · Spark | 7B | ~6 GB | marco-o1:7b |
meditron 7B Ollama library | Chat | 30#235 | x86 · Spark | 7B | ~6 GB | meditron:7b |
medllama2 7B Ollama library | Chat | 30#236 | x86 · Spark | 7B | ~6 GB | medllama2:7b |
notus 7B Ollama library | Chat | 30#237 | x86 · Spark | 7B | ~6 GB | notus:7b |
nous-hermes 7B Ollama library | Chat | 30#238 | x86 · Spark | 7B | ~6 GB | nous-hermes:7b |
olmo-3 7B Ollama library | Chat | 30#239 | x86 · Spark | 7B | ~6 GB | olmo-3:7b |
olmo2 7B Ollama library | Chat | 30#240 | x86 · Spark | 7B | ~6 GB | olmo2:7b |
openchat 7B Ollama library | Chat | 30#241 | x86 · Spark | 7B | ~6 GB | openchat:7b |
openthinker 7B Ollama library | Chat | 30#242 | x86 · Spark | 7B | ~6 GB | openthinker:7b |
orca-mini 7B Ollama library | Chat | 30#243 | x86 · Spark | 7B | ~6 GB | orca-mini:7b |
orca2 7B Ollama library | Chat | 30#244 | x86 · Spark | 7B | ~6 GB | orca2:7b |
stable-beluga 7B Ollama library | Chat | 30#245 | x86 · Spark | 7B | ~6 GB | stable-beluga:7b |
starling-lm 7B Ollama library | Chat | 30#246 | x86 · Spark | 7B | ~6 GB | starling-lm:7b |
vicuna 7B Ollama library | Chat | 30#247 | x86 · Spark | 7B | ~6 GB | vicuna:7b |
wizard-math 7B Ollama library | Chat | 30#248 | x86 · Spark | 7B | ~6 GB | wizard-math:7b |
wizard-vicuna-uncensored 7B Ollama library | Chat | 30#249 | x86 · Spark | 7B | ~6 GB | wizard-vicuna-uncensored:7b |
wizardlm 7B Ollama library | Chat | 30#250 | x86 · Spark | 7B | ~6 GB | wizardlm:7b-q4_K_M |
wizardlm2 7B Ollama library | Chat | 30#251 | x86 · Spark | 7B | ~6 GB | wizardlm2:7b |
xwinlm 7B Ollama library | Chat | 30#252 | x86 · Spark | 7B | ~6 GB | xwinlm:7b |
yarn-llama2 7B Ollama library | Chat | 30#253 | x86 · Spark | 7B | ~6 GB | yarn-llama2:7b |
llava-phi3 3.8B Ollama library | Chat | 30#254 | x86 · Spark | 3.8B | ~5 GB | llava-phi3:3.8b |
nuextract 3.8B Ollama library | Chat | 30#255 | x86 · Spark | 3.8B | ~5 GB | nuextract:3.8b |
phi3 3.8B Microsoft | Chat | 30#256 | x86 · Spark | 3.8B | ~5 GB | phi3:3.8b |
phi3.5 3.8B Microsoft | Chat | 30#257 | x86 · Spark | 3.8B | ~5 GB | phi3.5:3.8b |
phi4-mini 3.8B Microsoft | Chat | 30#258 | x86 · Spark | 3.8B | ~5 GB | phi4-mini:3.8b |
phi4-mini-reasoning 3.8B Microsoft | Chat | 30#259 | x86 · Spark | 3.8B | ~5 GB | phi4-mini-reasoning:3.8b |
cogito 3B Ollama library | Chat | 29#260 | x86 · Spark | 3B | ~4 GB | cogito:3b |
granite4 3B IBM | Chat | 29#261 | x86 · Spark | 3B | ~4 GB | granite4:3b |
llama3.2 3B Meta | Chat | 29#262 | x86 · Spark | 3B | ~4 GB | llama3.2:3b |
qwen2.5 3B Alibaba | Chat | 29#263 | x86 · Spark | 3B | ~4 GB | qwen2.5:3b |
qwen2.5vl 3B Alibaba | Chat | 29#264 | x86 · Spark | 3B | ~4 GB | qwen2.5vl:3b |
smallthinker 3B Ollama library | Chat | 29#265 | x86 · Spark | 3B | ~4 GB | smallthinker:3b |
yi 6B 01.AI | Chat | 28#266 | x86 · Spark | 6B | ~6 GB | yi:6b |
dolphin-phi 2.7B Ollama library | Chat | 28#267 | x86 · Spark | 2.7B | ~4 GB | dolphin-phi:2.7b |
phi 2.7B Microsoft | Chat | 28#268 | x86 · Spark | 2.7B | ~4 GB | phi:2.7b |
laguna-xs-2.1 33B-A3B Poolside | Chat | 27#269 | x86 · Spark | 33B | ~23 GB | laguna-xs-2.1:q4_K_M |
laguna-xs.2 33B-A3B Poolside | Chat | 27#270 | x86 · Spark | 33B | ~23 GB | laguna-xs.2:q4_K_M |
glm-5.1 5B Zhipu | Chat | 27#271 | x86 · Spark | 5B | ~5 GB | glm-5.1 |
exaone3.5 2.4B Ollama library | Chat | 27#272 | x86 · Spark | 2.4B | ~4 GB | exaone3.5:2.4b |
gemma 2B Google | Chat | 26#273 | x86 · Spark | 2B | ~4 GB | gemma:2b |
gemma2 2B Google | Chat | 26#274 | x86 · Spark | 2B | ~4 GB | gemma2:2b |
gemma3n 2B Google | Chat | 26#275 | x86 · Spark | 2B | ~4 GB | gemma3n:2b |
granite3.2-vision 2B IBM | Chat | 26#276 | x86 · Spark | 2B | ~4 GB | granite3.2-vision:2b |
granite3.3 2B IBM | Chat | 26#277 | x86 · Spark | 2B | ~4 GB | granite3.3:2b |
qwen3-vl 2B Alibaba | Chat | 26#278 | x86 · Spark | 2B | ~4 GB | qwen3-vl:2b |
qwen3.5 2B Alibaba | Chat | 26#279 | x86 · Spark | 2B | ~4 GB | qwen3.5:2b |
shieldgemma 2B Ollama library | Chat | 26#280 | x86 · Spark | 2B | ~4 GB | shieldgemma:2b |
qwen 1.8B Alibaba | Chat | 25#281 | x86 · Spark | 1.8B | ~3 GB | qwen:1.8b |
qwen3 1.7B Alibaba | Chat | 25#282 | x86 · Spark | 1.7B | ~3 GB | qwen3:1.7b |
lfm2 24B-A2B Ollama library | Chat | 24#283 | x86 · Spark | 24B | ~17 GB | lfm2:24b |
deepscaler 1.5B Ollama library | Chat | 24#284 | x86 · Spark | 1.5B | ~3 GB | deepscaler:1.5b |
qwen2 1.5B Alibaba | Chat | 24#285 | x86 · Spark | 1.5B | ~3 GB | qwen2:1.5b |
qwen2-math 1.5B Alibaba | Chat | 24#286 | x86 · Spark | 1.5B | ~3 GB | qwen2-math:1.5b |
qwen2.5 1.5B Alibaba | Chat | 24#287 | x86 · Spark | 1.5B | ~3 GB | qwen2.5:1.5b |
deepseek-ocr 3B DeepSeek | Chat | 22#288 | x86 · Spark | 3B | ~4 GB | deepseek-ocr:3b |
falcon3 3B TII | Chat | 22#289 | x86 · Spark | 3B | ~4 GB | falcon3:3b |
granite3-moe 3B IBM | Chat | 22#290 | x86 · Spark | 3B | ~4 GB | granite3-moe:3b |
granite3.1-moe 3B IBM | Chat | 22#291 | x86 · Spark | 3B | ~4 GB | granite3.1-moe:3b |
granite4.1 3B IBM | Chat | 22#292 | x86 · Spark | 3B | ~4 GB | granite4.1:3b |
hermes3 3B Ollama library | Chat | 22#293 | x86 · Spark | 3B | ~4 GB | hermes3:3b |
ministral-3 3B Mistral | Chat | 22#294 | x86 · Spark | 3B | ~4 GB | ministral-3:3b |
orca-mini 3B Ollama library | Chat | 22#295 | x86 · Spark | 3B | ~4 GB | orca-mini:3b |
stablelm-zephyr 3B Ollama library | Chat | 22#296 | x86 · Spark | 3B | ~4 GB | stablelm-zephyr:3b |
tinydolphin 1.1B Ollama library | Chat | 22#297 | x86 · Spark | 1.1B | ~3 GB | tinydolphin:1.1b |
gemma3 1B Google | Chat | 22#298 | x86 · Spark | 1B | ~3 GB | gemma3:1b |
granite4 1B IBM | Chat | 22#299 | x86 · Spark | 1B | ~3 GB | granite4:1b |
llama3.2 1B Meta | Chat | 22#300 | x86 · Spark | 1B | ~3 GB | llama3.2:1b |
exaone-deep 2.4B Ollama library | Chat | 21#301 | x86 · Spark | 2.4B | ~4 GB | exaone-deep:2.4b |
qwen3.5 0.8B Alibaba | Chat | 21#302 | x86 · Spark | 800M | ~3 GB | qwen3.5:0.8b |
granite3-guardian 2B IBM | Chat | 20#303 | x86 · Spark | 2B | ~4 GB | granite3-guardian:2b |
granite3.1-dense 2B IBM | Chat | 20#304 | x86 · Spark | 2B | ~4 GB | granite3.1-dense:2b |
granite3.2 2B IBM | Chat | 20#305 | x86 · Spark | 2B | ~4 GB | granite3.2:2b |
qwen3 0.6B Alibaba | Chat | 20#306 | x86 · Spark | 600M | ~3 GB | qwen3:0.6b |
internlm2 1.8B Ollama library | Chat | 19#307 | x86 · Spark | 1.8B | ~3 GB | internlm2:1.8b |
moondream 1.8B Ollama library | Chat | 19#308 | x86 · Spark | 1.8B | ~3 GB | moondream:1.8b |
smollm 1.7B Ollama library | Chat | 19#309 | x86 · Spark | 1.7B | ~3 GB | smollm:1.7b |
smollm2 1.7B Ollama library | Chat | 19#310 | x86 · Spark | 1.7B | ~3 GB | smollm2:1.7b |
qwen 0.5B Alibaba | Chat | 19#311 | x86 · Spark | 500M | ~3 GB | qwen:0.5b |
qwen2 0.5B Alibaba | Chat | 19#312 | x86 · Spark | 500M | ~3 GB | qwen2:0.5b |
qwen2.5 0.5B Alibaba | Chat | 19#313 | x86 · Spark | 500M | ~3 GB | qwen2.5:0.5b |
stablelm2 1.6B Ollama library | Chat | 18#314 | x86 · Spark | 1.6B | ~3 GB | stablelm2:1.6b |
lfm2.5 8B-A1B Ollama library | Chat | 18#315 | x86 · Spark | 8B | ~7 GB | lfm2.5:8b |
deepseek-r1 1.5B DeepSeek | Chat | 18#316 | x86 · Spark | 1.5B | ~3 GB | deepseek-r1:1.5b |
reader-lm 1.5B Ollama library | Chat | 18#317 | x86 · Spark | 1.5B | ~3 GB | reader-lm:1.5b |
granite4 0.35B IBM | Chat | 18#318 | x86 · Spark | 350M | ~3 GB | granite4:350m |
functiongemma 0.27B Ollama library | Chat | 18#319 | x86 · Spark | 270M | ~3 GB | functiongemma:270m |
gemma3 0.27B Google | Chat | 18#320 | x86 · Spark | 270M | ~3 GB | gemma3:270m |
lfm2.5-thinking 1.2B Ollama library | Chat | 17#321 | x86 · Spark | 1.2B | ~3 GB | lfm2.5-thinking:1.2b |
tinyllama 1.1B Ollama library | Chat | 16#322 | x86 · Spark | 1.1B | ~3 GB | tinyllama:1.1b |
falcon3 1B TII | Chat | 16#323 | x86 · Spark | 1B | ~3 GB | falcon3:1b |
granite3-moe 1B IBM | Chat | 16#324 | x86 · Spark | 1B | ~3 GB | granite3-moe:1b |
granite3.1-moe 1B IBM | Chat | 16#325 | x86 · Spark | 1B | ~3 GB | granite3.1-moe:1b |
llama-guard3 1B Meta | Chat | 16#326 | x86 · Spark | 1B | ~3 GB | llama-guard3:1b |
minicpm-v4.6 1B Ollama library | Chat | 16#327 | x86 · Spark | 1B | ~3 GB | minicpm-v4.6:1b |
sailor2 1B Ollama library | Chat | 16#328 | x86 · Spark | 1B | ~3 GB | sailor2:1b |
reader-lm 0.5B Ollama library | Chat | 13#329 | x86 · Spark | 500M | ~3 GB | reader-lm:0.5b |
smollm 0.36B Ollama library | Chat | 12#330 | x86 · Spark | 360M | ~3 GB | smollm:360m |
smollm2 0.36B Ollama library | Chat | 12#331 | x86 · Spark | 360M | ~3 GB | smollm2:360m |
smollm 0.135B Ollama library | Chat | 11#332 | x86 · Spark | 135M | ~3 GB | smollm:135m |
smollm2 0.135B Ollama library | Chat | 11#333 | x86 · Spark | 135M | ~3 GB | smollm2:135m |
internlm2 0.001B Ollama library | Chat | 10#334 | x86 · Spark | 1M | ~3 GB | internlm2:1m |
GGUF catalog synced Jul 23, 2026, 12:13 PM from ollama.com/library sizes (GGUF — Ollama / LM Studio / llama.cpp) · memory estimate · size dominates Plan/Research/Build · fit is uncapped (higher wins)