Hardware

Apple M5

Apple M5 has 16 / 24 / 32 GB Unified and 153 GB/s. See which open models fit, at which quant, and roughly how fast. Figures below use the default memory (16 GB). Updated 2026-10-17.

Memory16 / 24 / 32 GB Unified

Bandwidth153 GB/s

Kindmac

Year2025

Apple: 153 GB/s, 16/24/32GB unified memory. Source.

RSS for new models on this device

Models that fit

Model	Verdict	Quant	Context	tok/s
GLM 4.7 Flash REAP 23B A3B 23.0B	Tight fit	Q3_K_S	8K	47–64
Kwaipilot KAT Coder V2.5 Dev 34.7B	Tight fit	IQ2_S	4K	40–55
Qwen3.5 35B A3B 34.7B	Tight fit	UD-IQ2_XXS	8K	77–105
Qwen3.6 35B A3B 34.7B	Tight fit	UD-IQ2_XXS	8K	77–104
Qwen2.5 7B Instruct 7.6B	Runs	Q8_0	8K	9.8–13
DeepSeek R1 Distill Qwen 7B 7.6B	Runs	Q8_0	8K	9.8–13
Qwen2.5 Coder 7B Instruct 128K 7.6B	Runs	Q8_0	8K	9.8–13
LFM2.5 24B A2B 24.0B	Tight fit	UD-IQ3_XXS	8K	59–81
GLM 4.7 Flash 29.9B	Tight fit	UD-IQ2_XXS	8K	31–43
gemma 4 26B A4B it 25.2B	Tight fit	UD-Q2_K_XL	8K	23–31
gemma 4 E4B it qat 7.5B	Runs great	UD-Q4_K_XL	8K	17–23
Qwen3 Coder 30B A3B Instruct 30.5B	Tight fit	UD-IQ2_XXS	8K	46–63
Qwen3 30B A3B Instruct 2507 30.5B	Tight fit	UD-IQ2_XXS	8K	46–63
Qwen3 VL 30B A3B Instruct 30.5B	Tight fit	UD-IQ2_XXS	8K	46–63
Qwen3 30B A3B Thinking 2507 30.5B	Tight fit	UD-IQ2_XXS	8K	46–63
LFM2.5 8B A1B 8.5B	Tight fit	UD-Q8_K_XL	8K	56–76
Qwen3.5 4B 4.2B	Runs	BF16	8K	9.7–13
Phi 4 mini instruct 3.8B	Runs	BF16	8K	9.6–13
Phi 4 mini reasoning 3.8B	Runs	BF16	8K	9.6–13
Ministral 3 3B Instruct 2512 3.4B	Runs great	Q8_0	8K	19–25
Ministral 3 3B Reasoning 2512 3.4B	Runs	BF16	8K	11–15
granite 4.0 h micro 3.2B	Runs great	BF16	8K	13–18
Llama 3.2 3B Instruct 3.2B	Runs	BF16	8K	11–16
Qwen2.5 3B Instruct 3.1B	Runs great	F16	8K	13–18
Qwen2.5 VL 3B Instruct 3.1B	Runs great	BF16	8K	13–18
SmolLM3 3B 3.1B	Runs	BF16	8K	12–17
LFM2.5 2.6B 2.7B	Runs great	BF16	8K	14–19
LFM2.5 VL 3B 2.7B	Runs great	BF16	8K	14–19
Qwen3.5 2B 1.9B	Runs great	BF16	8K	22–30
DeepSeek R1 Distill Qwen 1.5B 1.8B	Runs great	BF16	8K	22–30
Qwen3 1.7B 1.7B	Runs great	BF16	8K	19–26
Qwen3 VL 2B Instruct 1.7B	Runs great	BF16	8K	19–26
Qwen3 VL 2B Thinking 1.7B	Runs great	BF16	8K	19–26
Qwen2.5 1.5B Instruct 1.5B	Runs great	F16	8K	25–34
Qwen2.5 Coder 1.5B Instruct 1.5B	Runs great	F16	8K	25–34
Llama 3.2 1B Instruct 1.2B	Runs great	BF16	8K	31–42
LFM2.5 1.2B Instruct 1.2B	Runs great	BF16	8K	32–44
gemma 3 1b it 1.0B	Runs great	BF16	8K	38–52
Qwen3.5 0.8B 0.75B	Runs great	BF16	8K	52–71
Qwen3 0.6B 0.60B	Runs great	BF16	8K	39–54

90 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 M5 at Q3_K_S, 8K context, about 47–64 tok/s. Weights 9.59 GB plus 0.41 GB of KV cache — 10.4 GB of 11.0 GB usable. Weights shown in the verdict use GiB (the same 1024³ counting as GPU memory).