Machines we track

Memory size decides what fits. Memory bandwidth decides how fast it runs.

Machine	Memory	Bandwidth	From
Mac Studio M5 Ultra (96GB)	96 GB	1228.8 GB/s	$5,499	Check price →
Mac Studio M5 Ultra (256GB)	256 GB	1228.8 GB/s	$9,499	Check price →
Mac Studio M5 Max (40-core GPU, 64GB)	64 GB	614 GB/s	$3,799	Check price →
Mac mini M5 Pro (24GB)	24 GB	307 GB/s	$1,699	Check price →
Mac mini M5 Pro (64GB)	64 GB	307 GB/s		Check price →
Mac mini M4 Pro (64GB) older	64 GB	273 GB/s		Check price →
NVIDIA DGX Spark (128GB)	128 GB	273 GB/s		Check price →
Ryzen AI Max+ 395 mini PC (128GB)	128 GB	256 GB/s		Check price →
Mac mini M6 (16GB)	16 GB	170 GB/s	$899	Check price →
Mac mini M6 (32GB)	32 GB	170 GB/s		Check price →
Mac mini M4 (16GB) older	16 GB	120 GB/s		Check price →
Mac mini M2 (16GB) older	16 GB	100 GB/s		Check price →
Beelink SER7 (Ryzen 7 7840HS, 32GB)	32 GB	89.6 GB/s		Check price →
Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB)	32 GB	89.6 GB/s		Check price →
GEEKOM A6 (Ryzen 7 6800H, 32GB)	32 GB	76.8 GB/s		Check price →

All models

Qwen3.8 flash next 125B (A6B)ornith 1.5 9B ornith 1.5 35B Granite 4.2 3B Granite 4.2 8B Granite 4.2 30B Qwen3.8 27B Nemotron 3.5 lightning 30B (A3B)muse glimmer 30B ornith 9B ornith 35B lfm 2.5 8B (A1B)minicpm v4.5 8B minicpm v4.6 1B Mistral medium 3.5 128B Granite 4.1 3B Granite 4.1 8B Granite 4.1 30B Nemotron 3 33B Llama 3.1 8B Llama 3.1 70B DeepSeek-R1 1.5B DeepSeek-R1 7B DeepSeek-R1 8B DeepSeek-R1 14B DeepSeek-R1 32B DeepSeek-R1 70B Llama 3.2 1B Llama 3.2 3B Qwen2.5 3B Qwen2.5 7B Qwen2.5 14B Qwen2.5 32B Qwen2.5 72B Gemma 3 4B Gemma 3 12B Gemma 3 27B Qwen 3 1.7B Qwen 3 4B Qwen 3 8B Qwen 3 14B Qwen 3 30B (A3B)Qwen 3 32B Mistral 7B Gemma 2 2B Gemma 2 9B Gemma 2 27B Gemma 4 E2B Gemma 4 E4B Gemma 4 12B Gemma 4 31B Gemma 4 26B (A4B)Llama 3 8B Llama 3 70B Qwen2.5 Coder 3B Qwen2.5 Coder 7B Qwen2.5 Coder 14B Qwen2.5 Coder 32B Qwen3.5 2B Qwen3.5 4B Qwen3.5 9B Qwen3.5 27B Qwen3.5 35B (A3B)Qwen3.5 122B (A10B)Qwen3.5 0.8B Phi 3 3.8B Phi 3 14B LLaVA 7B LLaVA 13B LLaVA 34B gpt-oss 20B gpt-oss 120B Qwen3 Coder 30B (A3B)Gemma 2B Gemma 7B Qwen 7B Qwen 1.8B Qwen 4B Qwen 14B Qwen 32B Qwen 72B Qwen 110B Phi 4 14B Llama 2 7B Llama 2 13B Llama 2 70B Qwen3.6 27B Qwen3.6 35B (A3B)Code Llama 7B Code Llama 13B Code Llama 34B Code Llama 70B Qwen 3-VL 2B Qwen 3-VL 4B Qwen 3-VL 8B Qwen 3-VL 32B Qwen 3-VL 30B (A3B)Qwen2 7B Qwen2 72B Mistral nemo 12B minicpm v 8B Llama 3.2 Vision 11B Llama 3.2 Vision 90B Qwen2.5-VL 3B Qwen2.5-VL 7B Qwen2.5-VL 32B Qwen2.5-VL 72B DeepSeek Coder 6.7B DeepSeek Coder 33B Llama 3.3 70B dolPhin 3 8B smollm 2 1.7B OLMo 2 7B OLMo 2 13B codeGemma 2B codeGemma 7B Mistral small 22B Mistral small 24B DeepSeek Coder v2 16B orca mini 7B orca mini 13B orca mini 3B orca mini 70B Granite 3.1 moe 1B Granite 3.1 moe 3B starCoder 2 3B starCoder 2 7B starCoder 2 15B Nemotron 3 super 120B (A12B)mixtral 8X7B mixtral 8X22B Llama 2 uncensored 7B Llama 2 uncensored 70B falcon 3 1B falcon 3 3B falcon 3 7B falcon 3 10B Mistral small3.2 24B translateGemma 4B translateGemma 12B translateGemma 27B LLaVA Llama3 8B qwq 32B Gemma 3n E2B Gemma 3n E4B