Your rig

M1 Pro · 32 GB · 32 GB

32 GB unified · 200 GB/s · 24.0 GB addressable by the GPU
Edit hardware Export as JSON

Context length

KV cache at f16, 8K tokens

Quality floor
Q8_0 — near-lossless Q6_K Q5_K_M Q4_K_M — recommended Q3_K_M Q2_K — damaged
KV cache type
Runtime
Ollamallama.cppLM StudioMLX

4 of 5 runtimes drive this device.

Allow CPU offload Include partial-offload fits

Offloaded layers run at 60 GB/s host bandwidth — expect single-digit tokens per second.

Which one should I actually run?

Best models for your M1 Pro · 32 GB

Updated 8 Oct 2026 1 new this month

What do you want to do? Each row is the best-ranked model on that use case's shortlist that fits at Q4_K_M. The ordering is editorial; the sizes and speeds are computed. How the shortlists work.

RecommendationModelWhyQuant · totalTok/s est.
Best for writing
Your pick
Gemma 4 31B
Google · Apache 2.0
The cleanest, least verbose prose of the 2026 24–32 GB class. Q4_K_M · 20.2 GB 6.4 Runs great
Best overall Qwen3.8 27B
Alibaba · Apache 2.0
Best capability per gigabyte: a current-generation dense 27B with vision and 262K context. Q4_K_M · 16.7 GB 7.1 Runs great
Best for coding Qwen3.8 27B
Alibaba · Apache 2.0
Terminal-Bench 73, DeepSWE 42 — a generation ahead of anything else that fits 24 GB. Q4_K_M · 16.7 GB 7.1 Runs great
Best reasoning Gemma 4 31B
Google · Apache 2.0
89% AIME — the strongest maths of any model under 32B. Q4_K_M · 20.2 GB 6.4 Runs great
Best vision Qwen3.8 27B
Alibaba · Apache 2.0
Image and video in, OSWorld 84 — the strongest local vision-language model at 24 GB. Q4_K_M · 16.7 GB 7.1 Runs great
Best for agents Qwen3.8 27B
Alibaba · Apache 2.0
Computer use and tool calling are what 3.8 was trained for (OSWorld 84). Q4_K_M · 16.7 GB 7.1 Runs great
Best translation Qwen3.8 27B
Alibaba · Apache 2.0
119 languages, and Qwen translations read as idiomatic rather than literal. Q4_K_M · 16.7 GB 7.1 Runs great
Fastest good model Gemma 4 26B-A4B
Google · Apache 2.0
3.8B active and a small file — the quickest Gemma 4 with vision. Q4_K_M · 16.0 GB 24 Runs great
Best long context Qwen3.6 35B-A3B
Alibaba · Apache 2.0
262K with just 10 KV-cache layers and 2 KV heads: the cheapest long context at 24 GB. Q4_K_M · 23.3 GB
at 128K context
28 Tight fit

Everything that fits

Runs great

52 of 80 · fits with headroom for a longer prompt
ModelParamsQuantWeights +KV 8KTotal VRAM headroom Tok/sRuntime
Olmo 3.1 32B Instruct 32.2B Q4_K_M 18.1 GB 1.25 GB 20.0 GB
4.0 GB free
6.2 MLX Run
Nemotron 3.5 Lightning 30B-A3B 31.6B MoE / 3.2B act Q4_K_M 17.8 GB 0.05 GB 18.4 GB
5.6 GB free
29 MLX Run
Gemma 4 31B 31.3B Q4_K_M 17.6 GB 2.03 GB 20.2 GB
3.8 GB free
6.4 MLX Run
GLM-4.7-Flash 30B-A3B 31.2B MoE / 3B act Q4_K_M 17.5 GB 0.41 GB 18.6 GB
5.4 GB free
31 MLX Run
Qwen3 30B-A3B 30.5B MoE / 3.3B act Q4_K_M 17.1 GB 0.75 GB 18.5 GB
5.5 GB free
28 MLX Run
Qwen3 Coder 30B-A3B 30.5B MoE / 3.3B act Q4_K_M 17.1 GB 0.75 GB 18.5 GB
5.5 GB free
28 MLX Run
Muse Glimmer 30B 29.8B Q4_K_M 16.8 GB 0.18 GB 17.5 GB
6.5 GB free
6.7 MLX Run
Granite 4.1 30B 28.9B Q4_K_M 16.3 GB 2.00 GB 18.9 GB
5.1 GB free
6.9 MLX Run
Qwen3.8 27B 27.8B Q4_K_M 15.6 GB 0.50 GB 16.7 GB
7.3 GB free
7.1 MLX Run
Qwen3.6 27B 27.8B Q4_K_M 15.6 GB 0.50 GB 16.7 GB
7.3 GB free
7.1 MLX Run
Gemma 3 27B 27.4B Q4_K_M 15.4 GB 1.03 GB 17.0 GB
7.0 GB free
7.3 MLX Run
Gemma 4 26B-A4B 26.5B MoE / 3.8B act Q4_K_M 14.9 GB 0.51 GB 16.0 GB
8.0 GB free
24 MLX Run
Devstral Small 2 24B 24B Q4_K_M 13.5 GB 1.25 GB 15.3 GB
8.7 GB free
8.3 MLX Run
Mistral Small 3.2 24B 23.6B Q4_K_M 13.3 GB 1.25 GB 15.1 GB
8.9 GB free
8.4 MLX Run
gpt-oss 20B 20.9B MoE / 3.6B act MXFP4 10.8 GB 0.19 GB 11.6 GB
12.4 GB free
28 MLX Run
Qwen3 14B 14.8B Q4_K_M 8.3 GB 1.25 GB 10.2 GB
13.8 GB free
13 MLX Run
DeepSeek-R1-Distill-Qwen 14B 14.8B Q4_K_M 8.3 GB 1.50 GB 10.4 GB
13.6 GB free
13 MLX Run
Qwen2.5-Coder 14B 14.8B Q4_K_M 8.3 GB 1.50 GB 10.4 GB
13.6 GB free
13 MLX Run
Phi-4 14B 14.7B Q4_K_M 8.3 GB 1.56 GB 10.4 GB
13.6 GB free
14 MLX Run
Ministral 3 14B 13.9B Q4_K_M 7.8 GB 1.25 GB 9.7 GB
14.3 GB free
14 MLX Run
Gemma 3 12B 12.2B Q4_K_M 6.9 GB 0.81 GB 8.3 GB
15.7 GB free
16 MLX Run
Mistral NeMo 12B 12.2B Q4_K_M 6.9 GB 1.25 GB 8.7 GB
15.3 GB free
16 MLX Run
Gemma 4 12B 12B Q4_K_M 6.7 GB 0.81 GB 8.2 GB
15.8 GB free
17 MLX Run
Qwen3.5 9B 9.65B Q4_K_M 5.4 GB 0.25 GB 6.3 GB
17.7 GB free
21 MLX Run
Ornith 1.5 9B 9.41B Q4_K_M 5.3 GB 0.25 GB 6.1 GB
17.9 GB free
21 MLX Run
Ministral 3 8B 8.92B Q4_K_M 5.0 GB 1.06 GB 6.7 GB
17.3 GB free
22 MLX Run
Granite 4.1 8B 8.79B Q4_K_M 4.9 GB 1.25 GB 6.8 GB
17.2 GB free
23 MLX Run
LFM2.5 8B-A1B 8.47B MoE / 1.5B act Q4_K_M 4.8 GB 0.09 GB 5.5 GB
18.5 GB free
62 MLX Run
Fara 7B 8.29B Q4_K_M 4.7 GB 0.44 GB 5.7 GB
18.3 GB free
24 MLX Run
Qwen3 8B 8.19B Q4_K_M 4.6 GB 1.13 GB 6.3 GB
17.7 GB free
24 MLX Run
Llama 3.1 8B Instruct 8.03B Q4_K_M 4.5 GB 1.00 GB 6.1 GB
17.9 GB free
25 MLX Run
Gemma 4 E4B 8.0B Q4_K_M 4.5 GB 0.14 GB 5.2 GB
18.8 GB free
25 MLX Run
Ling 3.0 Tiny 7.9B-A1.3B 7.9B MoE / 1.3B act Q4_K_M 4.4 GB 0.05 GB 5.1 GB
18.9 GB free
71 MLX Run
DeepSeek-R1-Distill-Qwen 7B 7.62B Q4_K_M 4.3 GB 0.44 GB 5.3 GB
18.7 GB free
26 MLX Run
Qwen2.5-Coder 7B 7.62B Q4_K_M 4.3 GB 0.44 GB 5.3 GB
18.7 GB free
26 MLX Run
Olmo 3 7B Instruct 7.3B Q4_K_M 4.1 GB 2.50 GB 7.2 GB
16.8 GB free
27 MLX Run
Mistral 7B Instruct v0.3 7.25B Q4_K_M 4.1 GB 1.00 GB 5.7 GB
18.3 GB free
27 MLX Run
Gemma 4 E2B 5.1B Q4_K_M 2.9 GB 0.07 GB 3.5 GB
20.5 GB free
39 MLX Run
Qwen3.5 4B 4.66B Q4_K_M 2.6 GB 0.25 GB 3.5 GB
20.5 GB free
43 MLX Run
Gemma 3 4B 4.3B Q4_K_M 2.4 GB 0.30 GB 3.3 GB
20.7 GB free
46 MLX Run
Qwen3 4B 4.02B Q4_K_M 2.3 GB 1.13 GB 4.0 GB
20.0 GB free
49 MLX Run
Ministral 3 3B 3.85B Q4_K_M 2.2 GB 0.81 GB 3.6 GB
20.4 GB free
52 MLX Run
Phi-4-mini 3.8B 3.84B Q4_K_M 2.2 GB 1.00 GB 3.8 GB
20.2 GB free
52 MLX Run
Granite 4.1 3B 3.4B Q4_K_M 1.9 GB 0.63 GB 3.1 GB
20.9 GB free
58 MLX Run
Llama 3.2 3B Instruct 3.21B Q4_K_M 1.8 GB 0.88 GB 3.3 GB
20.7 GB free
62 MLX Run
LFM2.5 2.6B 2.7B Q4_K_M 1.5 GB 0.13 GB 2.2 GB
21.8 GB free
74 MLX Run
Qwen3.5 2B 2.27B Q4_K_M 1.3 GB 0.09 GB 2.0 GB
22.0 GB free
88 MLX Run
Qwen3 1.7B 1.72B Q4_K_M 1.0 GB 0.88 GB 2.4 GB
21.6 GB free
116 MLX Run
Llama 3.2 1B Instruct 1.24B Q4_K_M 0.7 GB 0.25 GB 1.5 GB
22.5 GB free
160 MLX Run
Gemma 3 1B 1.0B Q4_K_M 0.6 GB 0.04 GB 1.2 GB
22.8 GB free
199 MLX Run
Qwen3.5 0.8B 0.87B Q4_K_M 0.5 GB 0.09 GB 1.2 GB
22.8 GB free
228 MLX Run
Qwen3 0.6B 0.6B Q4_K_M 0.3 GB 0.88 GB 1.8 GB
22.2 GB free
331 MLX Run

Runs — tight

6 models · fits at 8K, drop context or quant to go longer
ModelParamsQuantWeights +KV 8KTotal VRAM headroom Tok/sRuntime
Qwen3.6 35B-A3B 35.9B MoE / 3.3B act Q4_K_M 20.2 GB 0.16 GB 20.9 GB
3.1 GB free
28 MLX Run
Ornith 1.5 35B-A3B 35.9B MoE / 3.3B act Q4_K_M 20.2 GB 0.16 GB 20.9 GB
3.1 GB free
28 MLX Run
LLM-jp 4 33B Thinking 33.2B Q4_K_M 18.7 GB 2.00 GB 21.3 GB
2.7 GB free
6.0 MLX Run
Qwen3 32B 32.8B Q4_K_M 18.4 GB 2.00 GB 21.0 GB
3.0 GB free
6.1 MLX Run
DeepSeek-R1-Distill-Qwen 32B 32.8B Q4_K_M 18.4 GB 2.00 GB 21.0 GB
3.0 GB free
6.1 MLX Run
Qwen2.5-Coder 32B 32.8B Q4_K_M 18.4 GB 2.00 GB 21.0 GB
3.0 GB free
6.1 MLX Run

Won't fit in VRAM

22 models · some are possible with CPU offload
ModelParamsQuantWeights +KV 8KTotal Over budget Tok/sRuntime
Kimi K3 2.8T-A104B 2780B MoE / 104B act Q4_K_M 1563.2 GB 0.21 GB 1564.0 GB +1540.0 GB ~0.9 MLX Why
Qwen3.8 2.4T-A95B 2446B MoE / 95B act Q4_K_M 1375.4 GB 0.72 GB 1376.7 GB +1352.7 GB ~1.0 MLX Why
DeepSeek V4 Pro 1.6T-A49B 1650B MoE / 49B act Q4_K_M 927.8 GB 0.54 GB 928.9 GB +904.9 GB ~1.9 MLX Why
Kimi K2.6 1T-A32B 1027B MoE / 32B act Q4_K_M 577.5 GB 0.54 GB 578.6 GB +554.6 GB ~2.9 MLX Why
GLM-5.2 744B-A40B 753B MoE / 40B act Q4_K_M 423.4 GB 0.69 GB 424.7 GB +400.7 GB ~2.3 MLX Why
GLM-5.3 744B-A40B 753B MoE / 40B act Q4_K_M 423.4 GB 0.69 GB 424.7 GB +400.7 GB ~2.3 MLX Why
DeepSeek-R1 671B 671B MoE / 37B act Q4_K_M 377.3 GB 0.54 GB 378.4 GB +354.4 GB ~2.5 MLX Why
DeepSeek V4.1 Flash 552B-A16B New 552B MoE / 16B act Q4_K_M 310.4 GB 0.04 GB 311.0 GB +287.0 GB ~5.8 DwarfStar Why
Qwen3.5 397B-A17B 403B MoE / 17B act Q4_K_M 226.6 GB 0.23 GB 227.4 GB +203.4 GB ~5.5 MLX Why
Ornith 1.5 397B-A17B 397B MoE / 17B act Q4_K_M 223.2 GB 0.23 GB 224.1 GB +200.1 GB ~5.5 MLX Why
GLM-5.3-Flash 320B-A18B 321B MoE / 18B act Q4_K_M 180.5 GB 0.09 GB 181.2 GB +157.2 GB ~5.2 MLX Why
DeepSeek V4 Flash 284B-A13B 284B MoE / 13B act Q4_K_M 159.7 GB 0.38 GB 160.7 GB +136.7 GB ~7.1 MLX Why
Qwen3 235B-A22B 235B MoE / 22B act Q4_K_M 132.1 GB 1.47 GB 134.2 GB +110.2 GB ~4.2 MLX Why
Qwen3.8-Flash-Next 180B-A6B 180B MoE / 6B act Q4_K_M 101.2 GB 0.19 GB 102.0 GB +78.0 GB ~15 MLX Why
Qwen3.5 122B-A10B 125B MoE / 10B act Q4_K_M 70.3 GB 0.19 GB 71.1 GB +47.1 GB ~9.3 MLX Why
Nemotron 3 Super 120B-A12B 124B MoE / 12B act Q4_K_M 69.7 GB 0.06 GB 70.4 GB +46.4 GB ~7.7 MLX Why
Ling 3.0 Flash 124B-A5B 124B MoE / 5.1B act Q4_K_M 69.7 GB 0.06 GB 70.4 GB +46.4 GB ~18 MLX Why
Mistral Small 4 119B-A6B 119B MoE / 6.5B act Q4_K_M 66.9 GB 0.18 GB 67.7 GB +43.7 GB ~14 MLX Why
gpt-oss 120B 117B MoE / 5.1B act MXFP4 60.5 GB 0.29 GB 61.4 GB +37.4 GB ~20 MLX Why
Llama 4 Scout 109B-A17B 109B MoE / 17B act Q4_K_M 61.3 GB 1.50 GB 63.4 GB +39.4 GB ~5.5 MLX Why
Llama 3.3 70B Instruct 70.6B Q4_K_M 39.7 GB 2.50 GB 42.8 GB +18.8 GB ~2.8 MLX Why
DeepSeek-R1-Distill-Llama 70B 70.6B Q4_K_M 39.7 GB 2.50 GB 42.8 GB +18.8 GB ~2.8 MLX Why

Totals = quantised weights + f16 KV cache at 8K tokens + 0.6 GB runtime overhead, against 24.0 GB usable unified memory. Tokens per second are estimated from 200 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.


Same memory, different speed

These machines have the same 24.0 GB usable, so they run exactly the models above. Generation speed scales with memory bandwidth.

DeviceBandwidthSpeed vs yours
M2 Pro · 32 GB
M2 Pro · 2023
200 GB/s same
M4 · 32 GB
M4 · 2024
120 GB/s 0.60×

Best LLM for a 32 GB Mac, with every machine in the class →

What more memory unlocks

At Q4_K_M and 8K context this machine fits 58 of 80 models. Each step up, and the largest models it adds:

Every device ranked by what it can run →