Local LLM Compatibility Dataset

90 models by params, quantization, and memory load — which run locally on Apple Silicon and NVIDIA GPUs. Free under CC BY 4.0. Updated 2026-06-15.

This is ModelFit's open compatibility dataset: every model the site tracks, with the parameter size, quantization, minimum RAM, and estimated memory load used to decide what runs locally. Reuse it freely with attribution (CC BY 4.0) — credit ModelFit (modelfit.io). Machine-readable version: /api/dataset/, or get the CSV + JSON on GitHub.

ModelFamilyParamsQuantMin RAMEst. loadLocalollama
Claude Fable 5Claude0BAPI0 GBCloud
Claude 3.5 SonnetClaude120BAPI0 GBCloud
Claude 3.7 SonnetClaude140BAPI0 GBCloud
Claude 4 SonnetClaude160BAPI0 GBCloud
Claude 3 OpusClaude220BAPI0 GBCloud
Claude 4 OpusClaude240BAPI0 GBCloud
Claude Opus 4.7Claude260BAPI0 GBCloud
Claude Opus 4.8Claude270BAPI0 GBCloud
DeepSeek-R1 Distill Qwen 7BDeepSeek7BQ4_K_M10 GB~5.5 GBYesdeepseek-r1:7b
DeepSeek-R1 Distill Qwen 14BDeepSeek14BQ4_K_M22 GB~11 GBYesdeepseek-r1:14b
DeepSeek-R1 Distill Llama 70BDeepSeek70BQ4_K_M48 GB~42 GBYesdeepseek-r1:70b
DeepSeek V4 FlashDeepSeek284BAPI0 GBCloud
DeepSeek-R1 671BDeepSeek671BQ4_K_M400 GB~380 GBYesdeepseek-r1:671b-q4_K_M
DeepSeek-V3DeepSeek671BAPI0 GBCloud
DeepSeek-V3-0324DeepSeek671BAPI0 GBCloud
DeepSeek-R1DeepSeek671BAPI0 GBCloud
DeepSeek V4 ProDeepSeek1600BAPI0 GBCloud
Gemma 3 1B InstructGemma1BQ4_K_M3 GB~1 GBYesgemma3:1b
Gemma 2 2B InstructGemma2BQ4_K_M5 GB~1.8 GBYesgemma2:2b-instruct-q4_K_M
Gemma 4 E2BGemma2.3BQ4_K_M4 GB~2.3 GBYesgemma4:e2b
Gemma 3 4B InstructGemma4BQ4_K_M8 GB~3.5 GBYesgemma3:4b
Gemma 4 E4BGemma4.5BQ4_K_M8 GB~4 GBYesgemma4:e4b
Gemma 2 9B InstructGemma9BQ4_K_M14 GB~7 GBYesgemma2:9b-instruct-q4_K_M
Gemma 3 12B InstructGemma12BQ4_K_M18 GB~9.5 GBYesgemma3:12b
Gemma 4 12BGemma12BQ4_K_M16 GB~8 GBYesgemma4:12b
Gemma 4 26B-A4BGemma26BQ4_K_M24 GB~16 GBYesgemma4:26b
Gemma 2 27B InstructGemma27BQ4_K_M28 GB~21 GBYesgemma2:27b-instruct-q4_K_M
Gemma 3 27B InstructGemma27BQ4_K_M28 GB~21 GBYesgemma3:27b
Gemma 4 31BGemma31BQ4_K_M32 GB~20 GBYesgemma4:31b
Gemini 2.5 FlashGoogle80BAPI0 GBCloud
Gemini 2.5 ProGoogle175BAPI0 GBCloud
Gemini 3.1 ProGoogle300BAPI0 GBCloud
Granite 4.1 3B InstructGranite3BQ4_K_M6 GB~2 GBYesgranite4.1:3b
Granite 4.1 8B InstructGranite8BQ4_K_M12 GB~5.5 GBYesgranite4.1:8b
Kimi K2 InstructKimi1000BAPI0 GBCloud
Kimi K2.6Kimi1000BAPI0 GBCloud
Kimi K2.7-CodeKimi1000BAPI0 GBCloud
LFM2.5 8B-A1BLFM28.3BQ4_K_M10 GB~5.5 GBYeslfm2.5:8b-a1b-q4_K_M
LFM2 24B-A2B InstructLFM224BQ4_K_M16 GB~14 GBYeslfm2:24b-a2b
Llama 3.2 1B InstructLlama1BQ4_K_M3 GB~1 GBYesllama3.2:1b-instruct-q4_K_M
Llama 3.2 3B InstructLlama3BQ4_K_M6 GB~2.5 GBYesllama3.2:3b-instruct-q4_K_M
Llama 3.1 8B InstructLlama8BQ4_K_M12 GB~6.5 GBYesllama3.1:8b-instruct-q4_K_M
Llama 3.1 8B Instruct (Q5)Llama8BQ5_K_M14 GB~8 GBYesllama3.1:8b-instruct-q5_K_M
Llama 3.1 70B InstructLlama70BQ4_K_M48 GB~42 GBYesllama3.1:70b-instruct-q4_K_M
Llama 3.3 70B InstructLlama70BQ4_K_M48 GB~42 GBYesllama3.3:70b-instruct-q4_K_M
Llama 4 ScoutLlama109BQ4_K_M80 GB~67 GBYesllama4:scout
Llama 4 MaverickLlama400BQ4_K_M256 GB~245 GBYesllama4:maverick
Llama 3.1 405B InstructLlama405BQ4_K_M256 GB~243 GBYesllama3.1:405b-instruct-q4_K_M
MiniMax M3MiniMax428BAPI0 GBCloud
Mistral 7B InstructMistral7BQ4_K_M10 GB~5.5 GBYesmistral:7b-instruct-q4_K_M
Mistral Nemo 12BMistral12BQ4_K_M18 GB~9.5 GBYesmistral-nemo:12b
Mistral Small 22BMistral22BQ4_K_M26 GB~17 GBYesmistral-small:22b
Mistral Small 3.1Mistral24BQ4_K_M24 GB~15 GBYesmistral-small3.1:24b
Mixtral 8x7B InstructMistral46.7BQ4_K_M36 GB~30 GBYesmixtral:8x7b
Mistral Medium 3.5Mistral128BAPI0 GBCloud
NVIDIA Nemotron 3 UltraNemotron550BAPI0 GBCloud
GPT-4o miniOpenAI40BAPI0 GBCloud
GPT-4oOpenAI200BAPI0 GBCloud
GPT-5.5OpenAI400BAPI0 GBCloud
Phi-3 Mini 3.8BPhi3.8BQ4_K_M7 GB~3.2 GBYesphi3:mini
Phi-4 Mini 3.8BPhi3.8BQ4_K_M7 GB~3.2 GBYesphi4-mini:3.8b
Phi-3 Medium 14BPhi14BQ4_K_M20 GB~11 GBYesphi3:medium
Phi-4 14BPhi14BQ4_K_M22 GB~11.5 GBYesphi4:14b-q4_K_M
Qwen3.7-PlusQwen0BAPI0 GBCloud
Qwen2.5 0.5B InstructQwen0.5BQ4_K_M2 GB~0.8 GBYesqwen2.5:0.5b-instruct-q4_K_M
Qwen3.5 0.8B InstructQwen0.8BQ4_K_M2 GB~0.8 GBYesqwen3.5:0.8b
Qwen2.5 1.5B InstructQwen1.5BQ4_K_M4 GB~1.5 GBYesqwen2.5:1.5b-instruct-q4_K_M
Qwen3.5 2B InstructQwen2BQ4_K_M4 GB~1.8 GBYesqwen3.5:2b
Qwen2.5 3B InstructQwen3BQ4_K_M6 GB~2.5 GBYesqwen2.5:3b-instruct-q4_K_M
Qwen3.5 4B InstructQwen4BQ4_K_M8 GB~3.5 GBYesqwen3.5:4b
Qwen2.5 7B InstructQwen7BQ4_K_M10 GB~5.5 GBYesqwen2.5:7b-instruct-q4_K_M
Qwen2.5 Coder 7BQwen7BQ4_K_M10 GB~5.5 GBYesqwen2.5-coder:7b
Qwen3 8BQwen8BQ4_K_M12 GB~6.5 GBYesqwen3:8b-q4_K_M
Qwen3.5 9B InstructQwen9BQ4_K_M14 GB~7 GBYesqwen3.5:9b
Qwen2.5 14B InstructQwen14BQ4_K_M20 GB~11 GBYesqwen2.5:14b-instruct-q4_K_M
Qwen2.5 Coder 14BQwen14BQ4_K_M22 GB~11 GBYesqwen2.5-coder:14b
Qwen3 14BQwen14BQ4_K_M20 GB~11 GBYesqwen3:14b-q4_K_M
Qwen3.5 27B InstructQwen27BQ4_K_M20 GB~16 GBYesqwen3.5:27b
Qwen3.6 27BQwen27BQ4_K_M24 GB~18 GBYesqwen3.6:27b
Qwen3 30BQwen30BQ4_K_M28 GB~22 GBYesqwen3:30b
Qwen3.5 35B-A3B InstructQwen35BQ4_K_M24 GB~20 GBYesqwen3.5:35b-a3b
Qwen3.6 35B-A3BQwen35BQ4_K_M24 GB~22 GBYesqwen3.6:35b-a3b
Qwen3.5 122B-A10B InstructQwen122BQ4_K_M96 GB~72 GBYesqwen3.5:122b-a10b
Qwen3 235B A22BQwen235BQ4_K_M192 GB~130 GBYesqwen3:235b-a22b-q4_K_M
SmolLM2 360MSmolLM0.36BQ4_K_M1 GB~0.5 GBYessmollm2:360m
Grok 4.3xAI314BAPI0 GBCloud
GLM-5.2Zhipu0BAPI0 GBCloud
GLM-5Zhipu32BAPI0 GBCloud
GLM-4 PlusZhipu80BAPI0 GBCloud
GLM-5.1Zhipu744BAPI0 GBCloud

Estimated load = approximate memory at Q4_K_M; estimates, not measured. See the hardware stats for RAM-tier guidance.