Your rig
M2 · 8 GB · 8 GB
Which one should I actually run?
Best models for your M2 · 8 GB
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 32K. The ordering is editorial; the sizes and speeds are computed. How the shortlists work.
| Recommendation | Model | Why | Quant · total | Tok/s est. | |
|---|---|---|---|---|---|
| Best overall | Qwen3.5 2B Alibaba · Apache 2.0 |
Runs on 4 GB, and still multimodal. | Q8_0 · 3.2 GB | 25 | Runs great |
| Best for coding | Qwen3.5 2B Alibaba · Apache 2.0 |
Autocomplete on 4 GB. | Q8_0 · 3.2 GB | 25 | Runs great |
| Best reasoning | Qwen3.5 2B Alibaba · Apache 2.0 |
Reasoning traces on 4 GB; expect long outputs. | Q8_0 · 3.2 GB | 25 | Runs great |
| Best for writing | Nothing on the writing shortlist fits this device at Q8_0 — drop the quality floor or allow CPU offload. | ||||
| Best vision | Qwen3.5 2B Alibaba · Apache 2.0 |
Multimodal on 4 GB. | Q8_0 · 3.2 GB | 25 | Runs great |
| Best for agents | Nothing on the agents & tool use shortlist fits this device at Q8_0 — drop the quality floor or allow CPU offload. | ||||
| Best translation | Qwen3.5 2B Alibaba · Apache 2.0 |
Phrase-level translation on 4 GB. | Q8_0 · 3.2 GB | 25 | Runs great |
| Fastest good model | Qwen3.5 2B Alibaba · Apache 2.0 |
Instant on anything. | Q8_0 · 3.2 GB | 25 | Runs great |
| Best long context | Qwen3.5 2B Alibaba · Apache 2.0 |
Long documents on 4 GB. | Q8_0 · 4.3 GB at 128K context |
25 | Runs great |
Everything that fits
Runs great
5 of 80 · fits with headroom for a longer prompt| Model | Params | Quant | Weights | +KV 32K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| LFM2.5 2.6B | 2.7B | Q8_0 | 2.7 GB | 0.50 GB | 3.8 GB |
1.6 GB free
|
21 | MLX | Run |
| Qwen3.5 2B | 2.27B | Q8_0 | 2.2 GB | 0.38 GB | 3.2 GB |
2.2 GB free
|
25 | MLX | Run |
| Llama 3.2 1B Instruct | 1.24B | Q8_0 | 1.2 GB | 1.00 GB | 2.8 GB |
2.6 GB free
|
46 | MLX | Run |
| Gemma 3 1B | 1.0B | Q8_0 | 1.0 GB | 0.14 GB | 1.7 GB |
3.7 GB free
|
56 | MLX | Run |
| Qwen3.5 0.8B | 0.87B | Q8_0 | 0.9 GB | 0.38 GB | 1.8 GB |
3.6 GB free
|
65 | MLX | Run |
Runs — tight
1 model · fits at 32K, drop context or quant to go longer| Model | Params | Quant | Weights | +KV 32K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3 0.6B | 0.6B | Q8_0 | 0.6 GB | 3.50 GB | 4.7 GB |
0.7 GB free
|
94 | MLX | Run |
Won't fit in VRAM
74 models · some are possible with CPU offload| Model | Params | Quant | Weights | +KV 32K | Total | Over budget | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Kimi K3 2.8T-A104B | 2780B MoE / 104B act | Q8_0 | 2750.9 GB | 0.84 GB | 2752.3 GB | +2746.9 GB | ~0.3 | MLX | Why |
| Qwen3.8 2.4T-A95B | 2446B MoE / 95B act | Q8_0 | 2420.4 GB | 2.88 GB | 2423.9 GB | +2418.5 GB | ~0.3 | MLX | Why |
| DeepSeek V4 Pro 1.6T-A49B | 1650B MoE / 49B act | Q8_0 | 1632.7 GB | 2.14 GB | 1635.5 GB | +1630.1 GB | ~0.5 | MLX | Why |
| Kimi K2.6 1T-A32B | 1027B MoE / 32B act | Q8_0 | 1016.2 GB | 2.14 GB | 1019.0 GB | +1013.6 GB | ~0.8 | MLX | Why |
| GLM-5.2 744B-A40B | 753B MoE / 40B act | Q8_0 | 745.1 GB | 2.74 GB | 748.5 GB | +743.1 GB | ~0.7 | MLX | Why |
| GLM-5.3 744B-A40B | 753B MoE / 40B act | Q8_0 | 745.1 GB | 2.74 GB | 748.5 GB | +743.1 GB | ~0.7 | MLX | Why |
| DeepSeek-R1 671B | 671B MoE / 37B act | Q8_0 | 664.0 GB | 2.14 GB | 666.7 GB | +661.3 GB | ~0.7 | MLX | Why |
| DeepSeek V4.1 Flash 552B-A16B New | 552B MoE / 16B act | Q8_0 | 546.2 GB | 0.15 GB | 547.0 GB | +541.6 GB | ~1.6 | DwarfStar | Why |
| Qwen3.5 397B-A17B | 403B MoE / 17B act | Q8_0 | 398.8 GB | 0.94 GB | 400.3 GB | +394.9 GB | ~1.6 | MLX | Why |
| Ornith 1.5 397B-A17B | 397B MoE / 17B act | Q8_0 | 392.8 GB | 0.94 GB | 394.4 GB | +389.0 GB | ~1.6 | MLX | Why |
| GLM-5.3-Flash 320B-A18B | 321B MoE / 18B act | Q8_0 | 317.6 GB | 0.34 GB | 318.6 GB | +313.2 GB | ~1.5 | MLX | Why |
| DeepSeek V4 Flash 284B-A13B | 284B MoE / 13B act | Q8_0 | 281.0 GB | 1.51 GB | 283.1 GB | +277.7 GB | ~2.0 | MLX | Why |
| Qwen3 235B-A22B | 235B MoE / 22B act | Q8_0 | 232.5 GB | 5.88 GB | 239.0 GB | +233.6 GB | ~1.2 | MLX | Why |
| Qwen3.8-Flash-Next 180B-A6B | 180B MoE / 6B act | Q8_0 | 178.1 GB | 0.75 GB | 179.5 GB | +174.1 GB | ~4.4 | MLX | Why |
| Qwen3.5 122B-A10B | 125B MoE / 10B act | Q8_0 | 123.7 GB | 0.75 GB | 125.0 GB | +119.6 GB | ~2.6 | MLX | Why |
| Nemotron 3 Super 120B-A12B | 124B MoE / 12B act | Q8_0 | 122.7 GB | 0.25 GB | 123.6 GB | +118.2 GB | ~2.2 | MLX | Why |
| Ling 3.0 Flash 124B-A5B | 124B MoE / 5.1B act | Q8_0 | 122.7 GB | 0.25 GB | 123.5 GB | +118.1 GB | ~5.2 | MLX | Why |
| Mistral Small 4 119B-A6B | 119B MoE / 6.5B act | Q8_0 | 117.8 GB | 0.70 GB | 119.1 GB | +113.7 GB | ~4.1 | MLX | Why |
| gpt-oss 120B | 117B MoE / 5.1B act | MXFP4 | 60.5 GB | 1.13 GB | 62.2 GB | +56.8 GB | ~9.9 | MLX | Why |
| Llama 4 Scout 109B-A17B | 109B MoE / 17B act | Q8_0 | 107.9 GB | 2.63 GB | 111.1 GB | +105.7 GB | ~1.6 | MLX | Why |
| Llama 3.3 70B Instruct | 70.6B | Q8_0 | 69.9 GB | 10.00 GB | 80.5 GB | +75.1 GB | ~0.8 | MLX | Why |
| DeepSeek-R1-Distill-Llama 70B | 70.6B | Q8_0 | 69.9 GB | 10.00 GB | 80.5 GB | +75.1 GB | ~0.8 | MLX | Why |
| Qwen3.6 35B-A3B | 35.9B MoE / 3.3B act | Q8_0 | 35.5 GB | 0.63 GB | 36.7 GB | +31.3 GB | ~8.0 | MLX | Why |
| Ornith 1.5 35B-A3B | 35.9B MoE / 3.3B act | Q8_0 | 35.5 GB | 0.63 GB | 36.7 GB | +31.3 GB | ~8.0 | MLX | Why |
| LLM-jp 4 33B Thinking | 33.2B | Q8_0 | 32.9 GB | 8.00 GB | 41.5 GB | +36.1 GB | ~1.7 | MLX | Why |
| Qwen3 32B | 32.8B | Q8_0 | 32.5 GB | 8.00 GB | 41.1 GB | +35.7 GB | ~1.7 | MLX | Why |
| DeepSeek-R1-Distill-Qwen 32B | 32.8B | Q8_0 | 32.5 GB | 8.00 GB | 41.1 GB | +35.7 GB | ~1.7 | MLX | Why |
| Qwen2.5-Coder 32B | 32.8B | Q8_0 | 32.5 GB | 8.00 GB | 41.1 GB | +35.7 GB | ~1.7 | MLX | Why |
| Olmo 3.1 32B Instruct | 32.2B | Q8_0 | 31.9 GB | 2.75 GB | 35.2 GB | +29.8 GB | ~1.8 | MLX | Why |
| Nemotron 3.5 Lightning 30B-A3B | 31.6B MoE / 3.2B act | Q8_0 | 31.3 GB | 0.19 GB | 32.1 GB | +26.7 GB | ~8.2 | MLX | Why |
| Gemma 4 31B | 31.3B | Q8_0 | 31.0 GB | 5.78 GB | 37.4 GB | +32.0 GB | ~1.8 | MLX | Why |
| GLM-4.7-Flash 30B-A3B | 31.2B MoE / 3B act | Q8_0 | 30.9 GB | 1.65 GB | 33.1 GB | +27.7 GB | ~8.8 | MLX | Why |
| Qwen3 30B-A3B | 30.5B MoE / 3.3B act | Q8_0 | 30.2 GB | 3.00 GB | 33.8 GB | +28.4 GB | ~8.0 | MLX | Why |
| Qwen3 Coder 30B-A3B | 30.5B MoE / 3.3B act | Q8_0 | 30.2 GB | 3.00 GB | 33.8 GB | +28.4 GB | ~8.0 | MLX | Why |
| Muse Glimmer 30B | 29.8B | Q8_0 | 29.5 GB | 0.48 GB | 30.6 GB | +25.2 GB | ~1.9 | MLX | Why |
| Granite 4.1 30B | 28.9B | Q8_0 | 28.6 GB | 8.00 GB | 37.2 GB | +31.8 GB | ~2.0 | MLX | Why |
| Qwen3.8 27B | 27.8B | Q8_0 | 27.5 GB | 2.00 GB | 30.1 GB | +24.7 GB | ~2.0 | MLX | Why |
| Qwen3.6 27B | 27.8B | Q8_0 | 27.5 GB | 2.00 GB | 30.1 GB | +24.7 GB | ~2.0 | MLX | Why |
| Gemma 3 27B | 27.4B | Q8_0 | 27.1 GB | 2.91 GB | 30.6 GB | +25.2 GB | ~2.1 | MLX | Why |
| Gemma 4 26B-A4B | 26.5B MoE / 3.8B act | Q8_0 | 26.2 GB | 1.45 GB | 28.3 GB | +22.9 GB | ~6.9 | MLX | Why |
| Devstral Small 2 24B | 24B | Q8_0 | 23.7 GB | 5.00 GB | 29.3 GB | +23.9 GB | ~2.4 | MLX | Why |
| Mistral Small 3.2 24B | 23.6B | Q8_0 | 23.4 GB | 5.00 GB | 29.0 GB | +23.6 GB | ~2.4 | MLX | Why |
| gpt-oss 20B | 20.9B MoE / 3.6B act | MXFP4 | 10.8 GB | 0.75 GB | 12.2 GB | +6.8 GB | ~14 | MLX | Why |
| Qwen3 14B | 14.8B | Q8_0 | 14.6 GB | 5.00 GB | 20.2 GB | +14.8 GB | ~3.8 | MLX | Why |
| DeepSeek-R1-Distill-Qwen 14B | 14.8B | Q8_0 | 14.6 GB | 6.00 GB | 21.2 GB | +15.8 GB | ~3.8 | MLX | Why |
| Qwen2.5-Coder 14B | 14.8B | Q8_0 | 14.6 GB | 6.00 GB | 21.2 GB | +15.8 GB | ~3.8 | MLX | Why |
| Phi-4 14B | 14.7B | Q8_0 | 14.5 GB | 3.13 GB | 18.3 GB | +12.9 GB | ~3.8 | MLX | Why |
| Ministral 3 14B | 13.9B | Q8_0 | 13.8 GB | 5.00 GB | 19.4 GB | +14.0 GB | ~4.1 | MLX | Why |
| Gemma 3 12B | 12.2B | Q8_0 | 12.1 GB | 2.31 GB | 15.0 GB | +9.6 GB | ~4.6 | MLX | Why |
| Mistral NeMo 12B | 12.2B | Q8_0 | 12.1 GB | 5.00 GB | 17.7 GB | +12.3 GB | ~4.6 | MLX | Why |
| Gemma 4 12B | 12B | Q8_0 | 11.9 GB | 2.31 GB | 14.8 GB | +9.4 GB | ~4.7 | MLX | Why |
| Qwen3.5 9B | 9.65B | Q8_0 | 9.5 GB | 1.00 GB | 11.1 GB | +5.7 GB | ~5.9 | MLX | Why |
| Ornith 1.5 9B | 9.41B | Q8_0 | 9.3 GB | 1.00 GB | 10.9 GB | +5.5 GB | ~6.0 | MLX | Why |
| Ministral 3 8B | 8.92B | Q8_0 | 8.8 GB | 4.25 GB | 13.7 GB | +8.3 GB | ~6.3 | MLX | Why |
| Granite 4.1 8B | 8.79B | Q8_0 | 8.7 GB | 5.00 GB | 14.3 GB | +8.9 GB | ~6.4 | MLX | Why |
| LFM2.5 8B-A1B | 8.47B MoE / 1.5B act | Q8_0 | 8.4 GB | 0.38 GB | 9.4 GB | +4.0 GB | ~18 | MLX | Why |
| Fara 7B | 8.29B | Q8_0 | 8.2 GB | 1.75 GB | 10.6 GB | +5.2 GB | ~6.8 | MLX | Why |
| Qwen3 8B | 8.19B | Q8_0 | 8.1 GB | 4.50 GB | 13.2 GB | +7.8 GB | ~6.9 | MLX | Why |
| Llama 3.1 8B Instruct | 8.03B | Q8_0 | 7.9 GB | 4.00 GB | 12.5 GB | +7.1 GB | ~7.0 | MLX | Why |
| Gemma 4 E4B | 8.0B | Q8_0 | 7.9 GB | 0.47 GB | 9.0 GB | +3.6 GB | ~7.1 | MLX | Why |
| Ling 3.0 Tiny 7.9B-A1.3B | 7.9B MoE / 1.3B act | Q8_0 | 7.8 GB | 0.21 GB | 8.6 GB | +3.2 GB | ~20 | MLX | Why |
| DeepSeek-R1-Distill-Qwen 7B | 7.62B | Q8_0 | 7.5 GB | 1.75 GB | 9.9 GB | +4.5 GB | ~7.4 | MLX | Why |
| Qwen2.5-Coder 7B | 7.62B | Q8_0 | 7.5 GB | 1.75 GB | 9.9 GB | +4.5 GB | ~7.4 | MLX | Why |
| Olmo 3 7B Instruct | 7.3B | Q8_0 | 7.2 GB | 5.50 GB | 13.3 GB | +7.9 GB | ~7.7 | MLX | Why |
| Mistral 7B Instruct v0.3 | 7.25B | Q8_0 | 7.2 GB | 4.00 GB | 11.8 GB | +6.4 GB | ~7.8 | MLX | Why |
| Gemma 4 E2B | 5.1B | Q8_0 | 5.0 GB | 0.23 GB | 5.9 GB | +0.5 GB | ~11 | MLX | Why |
| Qwen3.5 4B | 4.66B | Q8_0 | 4.6 GB | 1.00 GB | 6.2 GB | +0.8 GB | ~12 | MLX | Why |
| Gemma 3 4B | 4.3B | Q8_0 | 4.3 GB | 0.86 GB | 5.7 GB | +0.3 GB | ~13 | MLX | Why |
| Qwen3 4B | 4.02B | Q8_0 | 4.0 GB | 4.50 GB | 9.1 GB | +3.7 GB | ~14 | MLX | Why |
| Ministral 3 3B | 3.85B | Q8_0 | 3.8 GB | 3.25 GB | 7.7 GB | +2.3 GB | ~15 | MLX | Why |
| Phi-4-mini 3.8B | 3.84B | Q8_0 | 3.8 GB | 4.00 GB | 8.4 GB | +3.0 GB | ~15 | MLX | Why |
| Granite 4.1 3B | 3.4B | Q8_0 | 3.4 GB | 2.50 GB | 6.5 GB | +1.1 GB | ~17 | MLX | Why |
| Llama 3.2 3B Instruct | 3.21B | Q8_0 | 3.2 GB | 3.50 GB | 7.3 GB | +1.9 GB | ~18 | MLX | Why |
| Qwen3 1.7B | 1.72B | Q8_0 | 1.7 GB | 3.50 GB | 5.8 GB | +0.4 GB | ~33 | MLX | Why |
Totals = quantised weights + f16 KV cache at 32K tokens + 0.6 GB runtime overhead, against 5.4 GB usable unified memory. Tokens per second are estimated from 100 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.
Same memory, different speed
These machines have the same 5.4 GB usable, so they run exactly the models above. Generation speed scales with memory bandwidth.
What more memory unlocks
At Q4_K_M and 8K context this machine fits 19 of 80 models. Each step up, and the largest models it adds:
| Step up | Models fit | Adds, largest first |
|---|---|---|
| 16 GB Mac e.g. M4 · 16 GB |
37 (+18) | Qwen3 14B, DeepSeek-R1-Distill-Qwen 14B, Qwen2.5-Coder 14B |
| 24 GB Mac e.g. M4 Pro · 24 GB |
45 (+26) | Muse Glimmer 30B, Qwen3.8 27B, Qwen3.6 27B |
| 32 GB Mac e.g. M4 · 32 GB |
58 (+39) | Qwen3.6 35B-A3B, Ornith 1.5 35B-A3B, LLM-jp 4 33B Thinking |