Yes — with 28.3 GB to spare
Mistral Small 4 119B-A6B at Q4_K_M fits your M3 Max · 128 GB entirely in unified memory at 8K context, at an estimated 29 tokens per second. There is room for its full 256K window.
Instruct, reasoning, vision and code in one 119B MoE. A latent KV cache (320 wide) keeps context cheap; the weights still want 64 GB+.
Hardware requirements What hardware do I need to run Mistral Small 4 119B-A6B? →At Q4_K_M with an 8K context: a 141 GB GPU (H200 SXM) or a 128 GB Mac. Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 117.8 GB | 118.5 GB | — | ~16 | −0.1% ppl | 22.5 GB over |
| Q6_K | 90.9 GB | 91.7 GB | 205K | 21 | −0.4% ppl | Long context |
| Q5_K_M | 78.5 GB | 79.3 GB | 256K | 24 | −0.8% ppl | Long context |
| Q4_K_M | 66.9 GB | 67.7 GB | 256K | 29 | −1.9% ppl | Recommended |
| Q3_K_M | 54.2 GB | 54.9 GB | 256K | 35 | −5.4% ppl | Long context |
| Q2_K | 46.4 GB | 47.2 GB | 256K | 41 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model uses multi-head latent attention, so its cache is a compressed latent rather than full K and V.
How to run it
$ pip install mlx-lm $ mlx_lm.generate --model mlx-community/Mistral-Small-4-119B-2603-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
Related models on an M3 Max · 128 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Mistral Small 3.2 24B 23.6B · same family |
Q4_K_M · 15.1 GB | 17 | Runs great |
| gpt-oss 120B 117B MoE · similar size |
MXFP4 · 61.4 GB | 39 | Runs great |
| Nemotron 3 Super 120B-A12B 124B MoE · similar size |
Q4_K_M · 70.4 GB | 15 | Runs great |
| Ling 3.0 Flash 124B-A5B 124B MoE · similar size |
Q4_K_M · 70.4 GB | 36 | Runs great |
| Qwen3.5 122B-A10B 125B MoE · similar size |
Q4_K_M · 71.1 GB | 19 | Runs great |
| Llama 4 Scout 109B-A17B 109B MoE · similar size |
Q4_K_M · 63.4 GB | 11 | Runs great |
| Qwen3.8-Flash-Next 180B-A6B 180B MoE · similar size |
Q4_K_M · 102.0 GB | — | Won't fit |
Mistral Small 4 119B-A6B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
67.7 GB | — | Won't fit |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
67.7 GB | — | Won't fit |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
67.7 GB | — | Won't fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
67.7 GB | ~5.5 | CPU offload |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
67.7 GB | ~5.5 | CPU offload |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
67.7 GB | — | Won't fit |
| DGX Spark · 128 GB 96.0 GB usable · 273 GB/s |
67.7 GB | 19 | Runs great |
| H200 SXM 139.4 GB usable · 4800 GB/s |
67.7 GB | 306 | Runs great |