Hardware

Apple M1 Pro

Apple M1 Pro has 16 / 32 GB Unified and 200 GB/s. See which open models fit, at which quant, and roughly how fast. Figures below use the default memory (16 GB). Updated 2026-10-24.

Memory16 / 32 GB Unified

Bandwidth200 GB/s

Kindmac

Year2021

200 GB/s. 16GB or 32GB unified memory. Source.

RSS for new models on this device

Models that fit

Model	Verdict	Quant	Context	tok/s
Qwen2.5 14B Instruct 14.8B	Tight fit	Q5_K_S	4K	9.9–14
Qwen3 14B 14.8B	Tight fit	Q5_K_S	4K	10–14
NousResearch Hermes 4 14B 14.8B	Tight fit	Q5_K_S	4K	10–14
Ministral 3 14B Instruct 2512 13.5B	Tight fit	UD-Q5_K_XL	8K	10–14
Ministral 3 14B Reasoning 2512 13.5B	Tight fit	UD-Q5_K_XL	8K	10–14
DeepSeek R1 Distill Qwen 14B 14.8B	Tight fit	Q4_K_M	8K	10–14
Qwen2.5 Coder 14B Instruct 128K 14.8B	Tight fit	Q4_K_M	8K	10–14
phi 4 14.7B	Tight fit	Q4_K_M	8K	10–14
Devstral Small 2 24B Instruct 2512 23.6B	Tight fit	Q3_K_S	4K	9.9–14
Mistral Small 3.2 24B Instruct 2506 23.6B	Tight fit	Q3_K_S	4K	9.9–14
Magistral Small 2509 23.6B	Tight fit	Q3_K_S	4K	9.9–14
Qwen3.6 14B A3B FableVibes 13.8B	Tight fit	Q5_K_M	8K	47–65
Qwen3.8 27B 27.3B	Tight fit	UD-Q2_K_XL	8K	11–14
Qwen2.5 32B Instruct 32.8B	Tight fit	IQ2_XXS	4K	11–15
Qwen3 32B 32.8B	Tight fit	UD-IQ2_XXS	4K	11–14
Qwen2.5 Coder 32B Instruct 32.8B	Tight fit	IQ2_XXS	4K	11–15
Qwen3 VL 32B Instruct 32.8B	Tight fit	UD-IQ2_XXS	4K	11–14
GLM 4 32B 0414 32.6B	Tight fit	UD-IQ2_XXS	8K	11–15
GLM 4.6V Flash 9.4B	Tight fit	Q8_0	8K	11–15
GLM Z1 9B 0414 9.4B	Tight fit	Q8_0	8K	11–15
GLM 4 9B 0414 9.4B	Tight fit	Q8_0	8K	11–15
Qwen3.8 9B Distill 9.2B	Tight fit	Q8_0	8K	11–15
Qwen3.5 9B 9.0B	Tight fit	Q8_0	8K	11–15
MiMo V2.6 Distill Qwen 9B 9.0B	Tight fit	Q8_0	8K	11–15
Qwythos 9B Claude Mythos 5 1M 9.0B	Tight fit	Q8_0	8K	11–15
Qwythos 9B v2 9.0B	Tight fit	Q8_0	8K	11–15
granite 4.2 8b 8.8B	Tight fit	Q8_0	8K	10–14
Ministral 3 8B Instruct 2512 8.5B	Tight fit	Q8_0	8K	11–15
Ministral 3 8B Reasoning 2512 8.5B	Tight fit	Q8_0	8K	11–15
Swift Qwen3.8 27B 27.3B	Tight fit	IQ2_S	8K	11–14
Qwen3.5 27B 26.9B	Runs	UD-IQ2_XXS	8K	12–16
Qwen3.6 27B 26.9B	Tight fit	UD-IQ2_XXS	8K	11–15
Qwen3 VL 8B Instruct 8.2B	Tight fit	Q8_0	8K	11–15
DeepSeek R1 0528 Qwen3 8B 8.2B	Tight fit	Q8_0	8K	11–15
Qwen3 8B 8.2B	Tight fit	Q8_0	8K	11–15
Qwen3 VL 8B Thinking 8.2B	Tight fit	Q8_0	8K	11–15
Apertus 8B Instruct 2509 8.1B	Tight fit	Q8_0	8K	11–16
DeepSeek R1 Distill Llama 8B 8.0B	Tight fit	UD-Q8_K_XL	4K	9.9–13
Llama 3.1 8B Instruct 8.0B	Tight fit	UD-Q8_K_XL	4K	9.9–13
GLM 4.7 Flash REAP 23B A3B 23.0B	Tight fit	Q3_K_S	8K	62–84

105 more models in the catalog do not fit this default profile, or ranked below the first 40 that do.

Example: Tight fit fully in unified memory on your Apple M1 Pro at Q5_K_S, 4K context, about 9.9–14 tok/s. Weights 9.56 GB plus 0.75 GB of KV cache — 10.7 GB of 11.0 GB usable. Weights shown in the verdict use GiB (the same 1024³ counting as GPU memory).