Your rig
M3 Ultra · 512 GB · 512 GB
512 GB unified · 800 GB/s · 384.0 GB addressable by the GPU
Which one should I actually run?
Best models for your M3 Ultra · 512 GB
What do you want to do? Each row is the best-ranked model on that use case's shortlist that fits at Q5_K_M and 32K. The ordering is editorial; the sizes and speeds are computed. How the shortlists work.
All
General assistantCodingReasoning & mathsWritingVisionAgents & tool useTranslationLow latencyLong context
| Recommendation | Model | Why | Quant · total | Tok/s est. | |
|---|---|---|---|---|---|
| Best overall | DeepSeek V4 Flash 284B-A13B New DeepSeek · MIT |
Frontier-adjacent at 13B active; the largest model a 128–192 GB machine runs at a useful speed. | Q5_K_M · 189.6 GB | 24 | Runs great |
| Best for coding | DeepSeek V4 Flash 284B-A13B New DeepSeek · MIT |
Frontier coding at 13B active for 128 GB+ machines. | Q5_K_M · 189.6 GB | 24 | Runs great |
| Best reasoning | DeepSeek V4 Flash 284B-A13B New DeepSeek · MIT |
Most of V4 Pro's reasoning at 13B active. | Q5_K_M · 189.6 GB | 24 | Runs great |
| Best for writing | Llama 3.3 70B Instruct Meta · Llama 3.3 Community |
The creative-writing favourite: consistent voice, takes direction, handles fiction framing. | Q5_K_M · 57.2 GB | 9.6 | Runs great |
| Best vision | Qwen3.8 27B New this week Alibaba · Apache 2.0 |
Image and video in, OSWorld 84 — the strongest local vision-language model at 24 GB. | Q5_K_M · 21.0 GB | 24 | Runs great |
| Best for agents | DeepSeek V4 Flash 284B-A13B New DeepSeek · MIT |
Long agent trajectories at 13B active. | Q5_K_M · 189.6 GB | 24 | Runs great |
| Best translation | Qwen3.8 27B New this week Alibaba · Apache 2.0 |
119 languages, and Qwen translations read as idiomatic rather than literal. | Q5_K_M · 21.0 GB | 24 | Runs great |
| Fastest good model | Qwen3.6 35B-A3B Alibaba · Apache 2.0 |
3.3B active per token: the fastest model that still competes with dense 27Bs. | Q5_K_M · 24.9 GB | 96 | Runs great |
| Best long context | DeepSeek V4 Flash 284B-A13B New DeepSeek · MIT |
A 1M-token window with a compressed latent cache. | Q5_K_M · 194.1 GB at 128K context |
24 | Runs great |
Everything that fits
Runs great
70 of 76 · fits with headroom for a longer prompt| Model | Params | Quant | Weights | +KV 32K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5 397B-A17B | 403B MoE / 17B act | Q5_K_M | 266.0 GB | 0.94 GB | 267.5 GB |
116.5 GB free
|
19 | MLX | Run |
| Ornith 1.5 397B-A17B New this week | 397B MoE / 17B act | Q5_K_M | 262.0 GB | 0.94 GB | 263.6 GB |
120.4 GB free
|
19 | MLX | Run |
| DeepSeek V4 Flash 284B-A13B New | 284B MoE / 13B act | Q5_K_M | 187.5 GB | 1.51 GB | 189.6 GB |
194.4 GB free
|
24 | MLX | Run |
| Qwen3 235B-A22B | 235B MoE / 22B act | Q5_K_M | 155.1 GB | 5.88 GB | 161.6 GB |
222.4 GB free
|
14 | MLX | Run |
| Qwen3.5 122B-A10B | 125B MoE / 10B act | Q5_K_M | 82.5 GB | 0.75 GB | 83.9 GB |
300.1 GB free
|
32 | MLX | Run |
| Nemotron 3 Super 120B-A12B | 124B MoE / 12B act | Q5_K_M | 81.8 GB | 0.25 GB | 82.7 GB |
301.3 GB free
|
26 | MLX | Run |
| Ling 3.0 Flash 124B-A5B New | 124B MoE / 5.1B act | Q5_K_M | 81.8 GB | 0.25 GB | 82.7 GB |
301.3 GB free
|
62 | MLX | Run |
| Mistral Small 4 119B-A6B | 119B MoE / 6.5B act | Q5_K_M | 78.5 GB | 0.70 GB | 79.9 GB |
304.1 GB free
|
49 | MLX | Run |
| gpt-oss 120B | 117B MoE / 5.1B act | MXFP4 | 60.5 GB | 1.13 GB | 62.2 GB |
321.8 GB free
|
79 | MLX | Run |
| Llama 4 Scout 109B-A17B | 109B MoE / 17B act | Q5_K_M | 71.9 GB | 2.63 GB | 75.2 GB |
308.8 GB free
|
19 | MLX | Run |
| Llama 3.3 70B Instruct | 70.6B | Q5_K_M | 46.6 GB | 10.00 GB | 57.2 GB |
326.8 GB free
|
9.6 | MLX | Run |
| DeepSeek-R1-Distill-Llama 70B | 70.6B | Q5_K_M | 46.6 GB | 10.00 GB | 57.2 GB |
326.8 GB free
|
9.6 | MLX | Run |
| Qwen3.6 35B-A3B | 35.9B MoE / 3.3B act | Q5_K_M | 23.7 GB | 0.63 GB | 24.9 GB |
359.1 GB free
|
96 | MLX | Run |
| Ornith 1.5 35B-A3B New this week | 35.9B MoE / 3.3B act | Q5_K_M | 23.7 GB | 0.63 GB | 24.9 GB |
359.1 GB free
|
96 | MLX | Run |
| LLM-jp 4 33B Thinking New this week | 33.2B | Q5_K_M | 21.9 GB | 8.00 GB | 30.5 GB |
353.5 GB free
|
20 | MLX | Run |
| Qwen3 32B | 32.8B | Q5_K_M | 21.7 GB | 8.00 GB | 30.3 GB |
353.7 GB free
|
21 | MLX | Run |
| DeepSeek-R1-Distill-Qwen 32B | 32.8B | Q5_K_M | 21.7 GB | 8.00 GB | 30.3 GB |
353.7 GB free
|
21 | MLX | Run |
| Qwen2.5-Coder 32B | 32.8B | Q5_K_M | 21.7 GB | 8.00 GB | 30.3 GB |
353.7 GB free
|
21 | MLX | Run |
| Olmo 3.1 32B Instruct | 32.2B | Q5_K_M | 21.3 GB | 2.75 GB | 24.6 GB |
359.4 GB free
|
21 | MLX | Run |
| Nemotron 3.5 Lightning 30B-A3B New | 31.6B MoE / 3.2B act | Q5_K_M | 20.9 GB | 0.19 GB | 21.6 GB |
362.4 GB free
|
99 | MLX | Run |
| Gemma 4 31B | 31.3B | Q5_K_M | 20.7 GB | 5.78 GB | 27.0 GB |
357.0 GB free
|
22 | MLX | Run |
| GLM-4.7-Flash 30B-A3B | 31.2B MoE / 3B act | Q5_K_M | 20.6 GB | 1.65 GB | 22.8 GB |
361.2 GB free
|
105 | MLX | Run |
| Qwen3 30B-A3B | 30.5B MoE / 3.3B act | Q5_K_M | 20.1 GB | 3.00 GB | 23.7 GB |
360.3 GB free
|
96 | MLX | Run |
| Qwen3 Coder 30B-A3B | 30.5B MoE / 3.3B act | Q5_K_M | 20.1 GB | 3.00 GB | 23.7 GB |
360.3 GB free
|
96 | MLX | Run |
| Muse Glimmer 30B New | 29.8B | Q5_K_M | 19.7 GB | 0.48 GB | 20.8 GB |
363.2 GB free
|
23 | MLX | Run |
| Granite 4.1 30B | 28.9B | Q5_K_M | 19.1 GB | 8.00 GB | 27.7 GB |
356.3 GB free
|
23 | MLX | Run |
| Qwen3.8 27B New this week | 27.8B | Q5_K_M | 18.4 GB | 2.00 GB | 21.0 GB |
363.0 GB free
|
24 | MLX | Run |
| Qwen3.6 27B | 27.8B | Q5_K_M | 18.4 GB | 2.00 GB | 21.0 GB |
363.0 GB free
|
24 | MLX | Run |
| Gemma 3 27B | 27.4B | Q5_K_M | 18.1 GB | 2.91 GB | 21.6 GB |
362.4 GB free
|
25 | MLX | Run |
| Gemma 4 26B-A4B | 26.5B MoE / 3.8B act | Q5_K_M | 17.5 GB | 1.45 GB | 19.5 GB |
364.5 GB free
|
83 | MLX | Run |
| Devstral Small 2 24B | 24B | Q5_K_M | 15.8 GB | 5.00 GB | 21.4 GB |
362.6 GB free
|
28 | MLX | Run |
| Mistral Small 3.2 24B | 23.6B | Q5_K_M | 15.6 GB | 5.00 GB | 21.2 GB |
362.8 GB free
|
29 | MLX | Run |
| gpt-oss 20B | 20.9B MoE / 3.6B act | MXFP4 | 10.8 GB | 0.75 GB | 12.2 GB |
371.8 GB free
|
112 | MLX | Run |
| Qwen3 14B | 14.8B | Q5_K_M | 9.8 GB | 5.00 GB | 15.4 GB |
368.6 GB free
|
46 | MLX | Run |
| DeepSeek-R1-Distill-Qwen 14B | 14.8B | Q5_K_M | 9.8 GB | 6.00 GB | 16.4 GB |
367.6 GB free
|
46 | MLX | Run |
| Qwen2.5-Coder 14B | 14.8B | Q5_K_M | 9.8 GB | 6.00 GB | 16.4 GB |
367.6 GB free
|
46 | MLX | Run |
| Phi-4 14B | 14.7B | Q5_K_M | 9.7 GB | 3.13 GB | 13.4 GB |
370.6 GB free
|
46 | MLX | Run |
| Ministral 3 14B | 13.9B | Q5_K_M | 9.2 GB | 5.00 GB | 14.8 GB |
369.2 GB free
|
49 | MLX | Run |
| Gemma 3 12B | 12.2B | Q5_K_M | 8.1 GB | 2.31 GB | 11.0 GB |
373.0 GB free
|
56 | MLX | Run |
| Mistral NeMo 12B | 12.2B | Q5_K_M | 8.1 GB | 5.00 GB | 13.7 GB |
370.3 GB free
|
56 | MLX | Run |
| Gemma 4 12B | 12B | Q5_K_M | 7.9 GB | 2.31 GB | 10.8 GB |
373.2 GB free
|
56 | MLX | Run |
| Qwen3.5 9B | 9.65B | Q5_K_M | 6.4 GB | 1.00 GB | 8.0 GB |
376.0 GB free
|
70 | MLX | Run |
| Ornith 1.5 9B New this week | 9.41B | Q5_K_M | 6.2 GB | 1.00 GB | 7.8 GB |
376.2 GB free
|
72 | MLX | Run |
| Ministral 3 8B | 8.92B | Q5_K_M | 5.9 GB | 4.25 GB | 10.7 GB |
373.3 GB free
|
76 | MLX | Run |
| Granite 4.1 8B | 8.79B | Q5_K_M | 5.8 GB | 5.00 GB | 11.4 GB |
372.6 GB free
|
77 | MLX | Run |
| LFM2.5 8B-A1B | 8.47B MoE / 1.5B act | Q5_K_M | 5.6 GB | 0.38 GB | 6.6 GB |
377.4 GB free
|
211 | MLX | Run |
| Fara 7B | 8.29B | Q5_K_M | 5.5 GB | 1.75 GB | 7.8 GB |
376.2 GB free
|
82 | MLX | Run |
| Qwen3 8B | 8.19B | Q5_K_M | 5.4 GB | 4.50 GB | 10.5 GB |
373.5 GB free
|
83 | MLX | Run |
| Llama 3.1 8B Instruct | 8.03B | Q5_K_M | 5.3 GB | 4.00 GB | 9.9 GB |
374.1 GB free
|
84 | MLX | Run |
| Gemma 4 E4B | 8.0B | Q5_K_M | 5.3 GB | 0.47 GB | 6.4 GB |
377.6 GB free
|
85 | MLX | Run |
| Ling 3.0 Tiny 7.9B-A1.3B New | 7.9B MoE / 1.3B act | Q5_K_M | 5.2 GB | 0.21 GB | 6.0 GB |
378.0 GB free
|
243 | MLX | Run |
| DeepSeek-R1-Distill-Qwen 7B | 7.62B | Q5_K_M | 5.0 GB | 1.75 GB | 7.4 GB |
376.6 GB free
|
89 | MLX | Run |
| Qwen2.5-Coder 7B | 7.62B | Q5_K_M | 5.0 GB | 1.75 GB | 7.4 GB |
376.6 GB free
|
89 | MLX | Run |
| Olmo 3 7B Instruct | 7.3B | Q5_K_M | 4.8 GB | 5.50 GB | 10.9 GB |
373.1 GB free
|
93 | MLX | Run |
| Mistral 7B Instruct v0.3 | 7.25B | Q5_K_M | 4.8 GB | 4.00 GB | 9.4 GB |
374.6 GB free
|
93 | MLX | Run |
| Gemma 4 E2B | 5.1B | Q5_K_M | 3.4 GB | 0.23 GB | 4.2 GB |
379.8 GB free
|
133 | MLX | Run |
| Qwen3.5 4B | 4.66B | Q5_K_M | 3.1 GB | 1.00 GB | 4.7 GB |
379.3 GB free
|
145 | MLX | Run |
| Gemma 3 4B | 4.3B | Q5_K_M | 2.8 GB | 0.86 GB | 4.3 GB |
379.7 GB free
|
157 | MLX | Run |
| Qwen3 4B | 4.02B | Q5_K_M | 2.7 GB | 4.50 GB | 7.8 GB |
376.2 GB free
|
168 | MLX | Run |
| Ministral 3 3B | 3.85B | Q5_K_M | 2.5 GB | 3.25 GB | 6.4 GB |
377.6 GB free
|
176 | MLX | Run |
| Phi-4-mini 3.8B | 3.84B | Q5_K_M | 2.5 GB | 4.00 GB | 7.1 GB |
376.9 GB free
|
176 | MLX | Run |
| Granite 4.1 3B | 3.4B | Q5_K_M | 2.2 GB | 2.50 GB | 5.3 GB |
378.7 GB free
|
199 | MLX | Run |
| Llama 3.2 3B Instruct | 3.21B | Q5_K_M | 2.1 GB | 3.50 GB | 6.2 GB |
377.8 GB free
|
211 | MLX | Run |
| LFM2.5 2.6B New | 2.7B | Q5_K_M | 1.8 GB | 0.50 GB | 2.9 GB |
381.1 GB free
|
251 | MLX | Run |
| Qwen3.5 2B | 2.27B | Q5_K_M | 1.5 GB | 0.38 GB | 2.5 GB |
381.5 GB free
|
298 | MLX | Run |
| Qwen3 1.7B | 1.72B | Q5_K_M | 1.1 GB | 3.50 GB | 5.2 GB |
378.8 GB free
|
394 | MLX | Run |
| Llama 3.2 1B Instruct | 1.24B | Q5_K_M | 0.8 GB | 1.00 GB | 2.4 GB |
381.6 GB free
|
546 | MLX | Run |
| Gemma 3 1B | 1.0B | Q5_K_M | 0.7 GB | 0.14 GB | 1.4 GB |
382.6 GB free
|
677 | MLX | Run |
| Qwen3.5 0.8B | 0.87B | Q5_K_M | 0.6 GB | 0.38 GB | 1.5 GB |
382.5 GB free
|
778 | MLX | Run |
| Qwen3 0.6B | 0.6B | Q5_K_M | 0.4 GB | 3.50 GB | 4.5 GB |
379.5 GB free
|
1129 | MLX | Run |
Won't fit in VRAM
6 models · some are possible with CPU offload| Model | Params | Quant | Weights | +KV 32K | Total | Over budget | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Kimi K3 2.8T-A104B New | 2780B MoE / 104B act | Q5_K_M | 1835.0 GB | 0.84 GB | 1836.5 GB | +1452.5 GB | ~3.0 | MLX | Why |
| Qwen3.8 2.4T-A95B New | 2446B MoE / 95B act | Q5_K_M | 1614.5 GB | 2.88 GB | 1618.0 GB | +1234.0 GB | ~3.3 | MLX | Why |
| DeepSeek V4 Pro 1.6T-A49B New | 1650B MoE / 49B act | Q5_K_M | 1089.1 GB | 2.14 GB | 1091.9 GB | +707.9 GB | ~6.4 | MLX | Why |
| Kimi K2.6 1T-A32B | 1027B MoE / 32B act | Q5_K_M | 677.9 GB | 2.14 GB | 680.6 GB | +296.6 GB | ~9.9 | MLX | Why |
| GLM-5.2 744B-A40B | 753B MoE / 40B act | Q5_K_M | 497.0 GB | 2.74 GB | 500.4 GB | +116.4 GB | ~7.9 | MLX | Why |
| DeepSeek-R1 671B | 671B MoE / 37B act | Q5_K_M | 442.9 GB | 2.14 GB | 445.7 GB | +61.7 GB | ~8.5 | MLX | Why |
Totals = quantised weights + f16 KV cache at 32K tokens + 0.6 GB runtime overhead, against 384.0 GB usable unified memory. Tokens per second are estimated from 800 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.