Hardware

Apple M4 Pro

Apple M4 Pro has 24 / 48 / 64 GB Unified and 273 GB/s. See which open models fit, at which quant, and roughly how fast. Figures below use the default memory (24 GB). Updated 2026-10-24.

Memory24 / 48 / 64 GB Unified

Bandwidth273 GB/s

Kindmac

Year2024

Apple: 273 GB/s, up to 64GB. Source.

RSS for new models on this device

Models that fit

Model	Verdict	Quant	Context	tok/s
GLM 4.7 Flash 29.9B	Tight fit	UD-Q4_K_XL	8K	36–49
Qwen3 Coder 30B A3B Instruct 30.5B	Tight fit	UD-Q4_K_XL	4K	70–96
Qwen3 30B A3B Instruct 2507 30.5B	Tight fit	UD-Q4_K_XL	4K	70–96
Qwen3 VL 30B A3B Instruct 30.5B	Tight fit	UD-Q4_K_XL	4K	70–96
Qwen3 30B A3B Thinking 2507 30.5B	Tight fit	UD-Q4_K_XL	4K	70–96
Qwen3.5 35B A3B 34.7B	Tight fit	UD-IQ4_XS	8K	89–122
Qwen3.6 35B A3B 34.7B	Tight fit	UD-IQ4_XS	8K	88–120
Tiel Coder 35B A3B 34.7B	Tight fit	UD-IQ4_XS	8K	88–120
Nemotron 3 Nano 30B A3B 31.6B	Tight fit	IQ4_NL	4K	77–105
LFM2.5 24B A2B 24.0B	Tight fit	UD-Q5_K_XL	4K	82–112
gemma 4 26B A4B it 25.2B	Tight fit	UD-Q4_K_XL	8K	32–43
GLM 4.7 Flash REAP 23B A3B 23.0B	Tight fit	UD-Q5_K_XL	8K	57–78
Kwaipilot KAT Coder V2.5 Dev 34.7B	Tight fit	Q3_K_L	8K	47–63
bottlecapai ThinkingCap gemma 4 26B A4B it 25.2B	Tight fit	Q4_K_M	4K	39–53
gpt oss 20b 20.9B	Runs	UD-Q8_K_XL	8K	37–51
Cyber Tiel Coder 35B A3B GGUF MTP 35.5B	Tight fit	Q3_K_M (est.)	8K	92–126
Qwen3.8 35B A3B Distill 35.5B	Tight fit	Q3_K_M	8K	90–123
Qwen3.6 14B A3B FableVibes 13.8B	Runs	Q8_0	8K	45–61
GLM 4.6V Flash 9.4B	Runs	UD-Q8_K_XL	8K	12–16
GLM Z1 9B 0414 9.4B	Runs	UD-Q8_K_XL	8K	12–16
GLM 4 9B 0414 9.4B	Runs	UD-Q8_K_XL	8K	12–16
Qwen3.8 9B Distill 9.2B	Runs great	Q8_0	8K	15–20
Qwen2.5 VL 7B Instruct 7.6B	Runs	BF16	8K	9.6–13
Qwen2.5 7B Instruct 7.6B	Runs	F16	8K	9.6–13
DeepSeek R1 Distill Qwen 7B 7.6B	Runs	F16	8K	9.6–13
Qwen2.5 Coder 7B Instruct 128K 7.6B	Runs	F16	8K	9.6–13
gemma 4 E4B it 7.5B	Runs	BF16	8K	9.5–13
NVIDIA Nemotron 3.5 Bolt E4B 7.5B	Runs	BF16	8K	9.5–13
gemma 4 E4B it qat 7.5B	Runs great	UD-Q4_K_XL	8K	31–42
LFM2.5 8B A1B 8.5B	Tight fit	BF16	8K	62–85
gemma 4 E2B it 4.6B	Runs great	BF16	8K	16–21
Qwen3.8 4B Distill 4.3B	Runs great	BF16	8K	17–23
Qwen3.5 4B 4.2B	Runs great	BF16	8K	17–24
Sharp Spark X2.5 4B 4.1B	Runs great	Q6_K	8K	31–42
Qwen3 4B 4.0B	Runs great	BF16	8K	16–22
Qwen3 VL 4B Instruct 4.0B	Runs great	BF16	8K	16–22
Qwen3 4B Thinking 2507 4.0B	Runs great	F16	8K	16–22
Qwen3 VL 4B Thinking 4.0B	Runs great	BF16	8K	16–22
NVIDIA Nemotron 3 Nano 4B 4.0B	Runs great	BF16	8K	16–22
gemma 3 4b it 3.9B	Runs great	BF16	8K	17–23

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 M4 Pro at UD-Q4_K_XL, 8K context, about 36–49 tok/s. Weights 16.3 GB plus 0.41 GB of KV cache — 17.2 GB of 18.0 GB usable. Up to 16K context still fits. Weights shown in the verdict use GiB (the same 1024³ counting as GPU memory).