Your rig

M4 · 16 GB · 16 GB

16 GB unified · 120 GB/s · 10.7 GB addressable by the GPU
Edit hardware Export as JSON

Context length

KV cache at f16, 128K 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 M4 · 16 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 Q8_0 and 128K. The ordering is editorial; the sizes and speeds are computed. How the shortlists work.

RecommendationModelWhyQuant · totalTok/s est.
Best overall Qwen3.5 2B
Alibaba · Apache 2.0
Runs on 4 GB, and still multimodal. Q8_0 · 4.3 GB 30 Runs great
Best for coding Qwen3.5 2B
Alibaba · Apache 2.0
Autocomplete on 4 GB. Q8_0 · 4.3 GB 30 Runs great
Best reasoning Qwen3.5 2B
Alibaba · Apache 2.0
Reasoning traces on 4 GB; expect long outputs. Q8_0 · 4.3 GB 30 Runs great
Best for writing Gemma 4 E4B
Google · Apache 2.0
Readable prose on a laptop. Q8_0 · 10.3 GB 8.5 Tight fit
Best vision Gemma 4 E2B
Google · Apache 2.0
Phone-class vision. Q8_0 · 6.5 GB 13 Runs great
Best for agents Qwen3.5 4B
Alibaba · Apache 2.0
Function calling in 8 GB. Q8_0 · 9.2 GB 15 Tight fit
Best translation Gemma 4 E4B
Google · Apache 2.0
140+ languages on a laptop. Q8_0 · 10.3 GB 8.5 Tight fit
Fastest good model LFM2.5 8B-A1B
Liquid AI · LFM Open License v1.0
1.5B active; designed for laptops without a GPU. Q8_0 · 10.4 GB 21 Tight fit
Best long context Qwen3.5 2B
Alibaba · Apache 2.0
Long documents on 4 GB. Q8_0 · 4.3 GB
at 128K context
30 Runs great

Everything that fits

Runs great

10 of 80 · fits with headroom for a longer prompt
ModelParamsQuantWeights +KV 128KTotal VRAM headroom Tok/sRuntime
Gemma 4 E2B 5.1B Q8_0 5.0 GB 0.89 GB 6.5 GB
4.2 GB free
13 MLX Run
Gemma 3 4B 4.3B Q8_0 4.3 GB 3.11 GB 8.0 GB
2.7 GB free
16 MLX Run
Qwen3 4B 4.02B Q8_0 4.0 GB 4.50 GB 9.1 GB
1.6 GB free
17 MLX Run
LFM2.5 2.6B 2.7B Q8_0 2.7 GB 2.00 GB 5.3 GB
5.4 GB free
25 MLX Run
Qwen3.5 2B 2.27B Q8_0 2.2 GB 1.50 GB 4.3 GB
6.4 GB free
30 MLX Run
Qwen3 1.7B 1.72B Q8_0 1.7 GB 3.50 GB 5.8 GB
4.9 GB free
39 MLX Run
Llama 3.2 1B Instruct 1.24B Q8_0 1.2 GB 4.00 GB 5.8 GB
4.9 GB free
55 MLX Run
Gemma 3 1B 1.0B Q8_0 1.0 GB 0.14 GB 1.7 GB
9.0 GB free
68 MLX Run
Qwen3.5 0.8B 0.87B Q8_0 0.9 GB 1.50 GB 3.0 GB
7.7 GB free
78 MLX Run
Qwen3 0.6B 0.6B Q8_0 0.6 GB 3.50 GB 4.7 GB
6.0 GB free
113 MLX Run

Runs — tight

4 models · fits at 128K, drop context or quant to go longer
ModelParamsQuantWeights +KV 128KTotal VRAM headroom Tok/sRuntime
LFM2.5 8B-A1B 8.47B MoE / 1.5B act Q8_0 8.4 GB 1.46 GB 10.4 GB
0.3 GB free
21 MLX Run
Gemma 4 E4B 8.0B Q8_0 7.9 GB 1.78 GB 10.3 GB
0.4 GB free
8.5 MLX Run
Ling 3.0 Tiny 7.9B-A1.3B 7.9B MoE / 1.3B act Q8_0 7.8 GB 0.84 GB 9.3 GB
1.4 GB free
24 MLX Run
Qwen3.5 4B 4.66B Q8_0 4.6 GB 4.00 GB 9.2 GB
1.5 GB free
15 MLX Run

Won't fit in VRAM

66 models · some are possible with CPU offload
ModelParamsQuantWeights +KV 128KTotal Over budget Tok/sRuntime
Kimi K3 2.8T-A104B 2780B MoE / 104B act Q8_0 2750.9 GB 3.38 GB 2754.9 GB +2744.2 GB ~0.3 MLX Why
Qwen3.8 2.4T-A95B 2446B MoE / 95B act Q8_0 2420.4 GB 11.50 GB 2432.5 GB +2421.8 GB ~0.3 MLX Why
DeepSeek V4 Pro 1.6T-A49B 1650B MoE / 49B act Q8_0 1632.7 GB 8.58 GB 1641.9 GB +1631.2 GB ~0.6 MLX Why
Kimi K2.6 1T-A32B 1027B MoE / 32B act Q8_0 1016.2 GB 8.58 GB 1025.4 GB +1014.7 GB ~1.0 MLX Why
GLM-5.2 744B-A40B 753B MoE / 40B act Q8_0 745.1 GB 10.97 GB 756.7 GB +746.0 GB ~0.8 MLX Why
GLM-5.3 744B-A40B 753B MoE / 40B act Q8_0 745.1 GB 10.97 GB 756.7 GB +746.0 GB ~0.8 MLX Why
DeepSeek-R1 671B 671B MoE / 37B act Q8_0 664.0 GB 8.58 GB 673.2 GB +662.5 GB ~0.9 MLX Why
DeepSeek V4.1 Flash 552B-A16B New 552B MoE / 16B act Q8_0 546.2 GB 0.57 GB 547.4 GB +536.7 GB ~2.0 DwarfStar Why
Qwen3.5 397B-A17B 403B MoE / 17B act Q8_0 398.8 GB 3.75 GB 403.1 GB +392.4 GB ~1.9 MLX Why
Ornith 1.5 397B-A17B 397B MoE / 17B act Q8_0 392.8 GB 3.75 GB 397.2 GB +386.5 GB ~1.9 MLX Why
GLM-5.3-Flash 320B-A18B 321B MoE / 18B act Q8_0 317.6 GB 1.38 GB 319.6 GB +308.9 GB ~1.8 MLX Why
DeepSeek V4 Flash 284B-A13B 284B MoE / 13B act Q8_0 281.0 GB 6.05 GB 287.7 GB +277.0 GB ~2.4 MLX Why
Qwen3 235B-A22B 235B MoE / 22B act Q8_0 232.5 GB 23.50 GB 256.6 GB +245.9 GB ~1.4 MLX Why
Qwen3.8-Flash-Next 180B-A6B 180B MoE / 6B act Q8_0 178.1 GB 3.00 GB 181.7 GB +171.0 GB ~5.3 MLX Why
Qwen3.5 122B-A10B 125B MoE / 10B act Q8_0 123.7 GB 3.00 GB 127.3 GB +116.6 GB ~3.2 MLX Why
Nemotron 3 Super 120B-A12B 124B MoE / 12B act Q8_0 122.7 GB 1.00 GB 124.3 GB +113.6 GB ~2.6 MLX Why
Ling 3.0 Flash 124B-A5B 124B MoE / 5.1B act Q8_0 122.7 GB 0.98 GB 124.3 GB +113.6 GB ~6.2 MLX Why
Mistral Small 4 119B-A6B 119B MoE / 6.5B act Q8_0 117.8 GB 2.81 GB 121.2 GB +110.5 GB ~4.9 MLX Why
gpt-oss 120B 117B MoE / 5.1B act MXFP4 60.5 GB 4.50 GB 65.6 GB +54.9 GB ~12 MLX Why
Llama 4 Scout 109B-A17B 109B MoE / 17B act Q8_0 107.9 GB 7.13 GB 115.6 GB +104.9 GB ~1.9 MLX Why
Llama 3.3 70B Instruct 70.6B Q8_0 69.9 GB 40.00 GB 110.5 GB +99.8 GB ~1.0 MLX Why
DeepSeek-R1-Distill-Llama 70B 70.6B Q8_0 69.9 GB 40.00 GB 110.5 GB +99.8 GB ~1.0 MLX Why
Qwen3.6 35B-A3B 35.9B MoE / 3.3B act Q8_0 35.5 GB 2.50 GB 38.6 GB +27.9 GB ~9.6 MLX Why
Ornith 1.5 35B-A3B 35.9B MoE / 3.3B act Q8_0 35.5 GB 2.50 GB 38.6 GB +27.9 GB ~9.6 MLX Why
LLM-jp 4 33B Thinking 33.2B Q8_0 32.9 GB 16.00 GB 49.5 GB +38.8 GB ~2.0 MLX Why
Qwen3 32B 32.8B Q8_0 32.5 GB 32.00 GB 65.1 GB +54.4 GB ~2.1 MLX Why
DeepSeek-R1-Distill-Qwen 32B 32.8B Q8_0 32.5 GB 32.00 GB 65.1 GB +54.4 GB ~2.1 MLX Why
Qwen2.5-Coder 32B 32.8B Q8_0 32.5 GB 32.00 GB 65.1 GB +54.4 GB ~2.1 MLX Why
Olmo 3.1 32B Instruct 32.2B Q8_0 31.9 GB 4.75 GB 37.2 GB +26.5 GB ~2.1 MLX Why
Nemotron 3.5 Lightning 30B-A3B 31.6B MoE / 3.2B act Q8_0 31.3 GB 0.75 GB 32.6 GB +21.9 GB ~9.9 MLX Why
Gemma 4 31B 31.3B Q8_0 31.0 GB 20.78 GB 52.4 GB +41.7 GB ~2.2 MLX Why
GLM-4.7-Flash 30B-A3B 31.2B MoE / 3B act Q8_0 30.9 GB 6.61 GB 38.1 GB +27.4 GB ~11 MLX Why
Qwen3 30B-A3B 30.5B MoE / 3.3B act Q8_0 30.2 GB 12.00 GB 42.8 GB +32.1 GB ~9.6 MLX Why
Qwen3 Coder 30B-A3B 30.5B MoE / 3.3B act Q8_0 30.2 GB 12.00 GB 42.8 GB +32.1 GB ~9.6 MLX Why
Muse Glimmer 30B 29.8B Q8_0 29.5 GB 1.70 GB 31.8 GB +21.1 GB ~2.3 MLX Why
Granite 4.1 30B 28.9B Q8_0 28.6 GB 32.00 GB 61.2 GB +50.5 GB ~2.3 MLX Why
Qwen3.8 27B 27.8B Q8_0 27.5 GB 8.00 GB 36.1 GB +25.4 GB ~2.4 MLX Why
Qwen3.6 27B 27.8B Q8_0 27.5 GB 8.00 GB 36.1 GB +25.4 GB ~2.4 MLX Why
Gemma 3 27B 27.4B Q8_0 27.1 GB 10.41 GB 38.1 GB +27.4 GB ~2.5 MLX Why
Gemma 4 26B-A4B 26.5B MoE / 3.8B act Q8_0 26.2 GB 5.20 GB 32.0 GB +21.3 GB ~8.3 MLX Why
Devstral Small 2 24B 24B Q8_0 23.7 GB 20.00 GB 44.3 GB +33.6 GB ~2.8 MLX Why
Mistral Small 3.2 24B 23.6B Q8_0 23.4 GB 20.00 GB 44.0 GB +33.3 GB ~2.9 MLX Why
gpt-oss 20B 20.9B MoE / 3.6B act MXFP4 10.8 GB 3.00 GB 14.4 GB +3.7 GB ~17 MLX Why
Qwen3 14B 14.8B Q8_0 14.6 GB 20.00 GB 35.2 GB +24.5 GB ~4.6 MLX Why
DeepSeek-R1-Distill-Qwen 14B 14.8B Q8_0 14.6 GB 24.00 GB 39.2 GB +28.5 GB ~4.6 MLX Why
Qwen2.5-Coder 14B 14.8B Q8_0 14.6 GB 24.00 GB 39.2 GB +28.5 GB ~4.6 MLX Why
Phi-4 14B 14.7B Q8_0 14.5 GB 3.13 GB 18.3 GB +7.6 GB ~4.6 MLX Why
Ministral 3 14B 13.9B Q8_0 13.8 GB 20.00 GB 34.4 GB +23.7 GB ~4.9 MLX Why
Gemma 3 12B 12.2B Q8_0 12.1 GB 8.31 GB 21.0 GB +10.3 GB ~5.6 MLX Why
Mistral NeMo 12B 12.2B Q8_0 12.1 GB 20.00 GB 32.7 GB +22.0 GB ~5.6 MLX Why
Gemma 4 12B 12B Q8_0 11.9 GB 8.31 GB 20.8 GB +10.1 GB ~5.6 MLX Why
Qwen3.5 9B 9.65B Q8_0 9.5 GB 4.00 GB 14.1 GB +3.4 GB ~7.0 MLX Why
Ornith 1.5 9B 9.41B Q8_0 9.3 GB 4.00 GB 13.9 GB +3.2 GB ~7.2 MLX Why
Ministral 3 8B 8.92B Q8_0 8.8 GB 17.00 GB 26.4 GB +15.7 GB ~7.6 MLX Why
Granite 4.1 8B 8.79B Q8_0 8.7 GB 20.00 GB 29.3 GB +18.6 GB ~7.7 MLX Why
Fara 7B 8.29B Q8_0 8.2 GB 6.84 GB 15.6 GB +4.9 GB ~8.2 MLX Why
Qwen3 8B 8.19B Q8_0 8.1 GB 18.00 GB 26.7 GB +16.0 GB ~8.3 MLX Why
Llama 3.1 8B Instruct 8.03B Q8_0 7.9 GB 16.00 GB 24.5 GB +13.8 GB ~8.4 MLX Why
DeepSeek-R1-Distill-Qwen 7B 7.62B Q8_0 7.5 GB 7.00 GB 15.1 GB +4.4 GB ~8.9 MLX Why
Qwen2.5-Coder 7B 7.62B Q8_0 7.5 GB 7.00 GB 15.1 GB +4.4 GB ~8.9 MLX Why
Olmo 3 7B Instruct 7.3B Q8_0 7.2 GB 9.50 GB 17.3 GB +6.6 GB ~9.3 MLX Why
Mistral 7B Instruct v0.3 7.25B Q8_0 7.2 GB 4.00 GB 11.8 GB +1.1 GB ~9.3 MLX Why
Ministral 3 3B 3.85B Q8_0 3.8 GB 13.00 GB 17.4 GB +6.7 GB ~18 MLX Why
Phi-4-mini 3.8B 3.84B Q8_0 3.8 GB 16.00 GB 20.4 GB +9.7 GB ~18 MLX Why
Granite 4.1 3B 3.4B Q8_0 3.4 GB 10.00 GB 14.0 GB +3.3 GB ~20 MLX Why
Llama 3.2 3B Instruct 3.21B Q8_0 3.2 GB 14.00 GB 17.8 GB +7.1 GB ~21 MLX Why

Totals = quantised weights + f16 KV cache at 128K tokens + 0.6 GB runtime overhead, against 10.7 GB usable unified memory. Tokens per second are estimated from 120 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.


Same memory, different speed

These machines have the same 10.7 GB usable, so they run exactly the models above. Generation speed scales with memory bandwidth.

DeviceBandwidthSpeed vs yours
M1 · 16 GB
M1 · 2020
68 GB/s 0.57×

Best LLM for a 16 GB Mac, with every machine in the class →

What more memory unlocks

At Q4_K_M and 8K context this machine fits 37 of 80 models. Each step up, and the largest models it adds:

Every device ranked by what it can run →