Yes — with 92.4 GB to spare
Ministral 3 3B at Q4_K_M fits your M1 Ultra · 128 GB entirely in unified memory at 8K context, at an estimated 207 tokens per second. There is room for its full 256K window.
Fully in unified memory
8K context
Q4_K_M · 2.2 GB
Apache 2.0
Released Dec 2025
Vision
Edge model with a vision encoder and a 256K window. Apache 2.0.
Hardware requirements What hardware do I need to run Ministral 3 3B? →At Q4_K_M with an 8K context: a 6 GB GPU (RTX 3060 Laptop) or a 8 GB Mac (M3). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
weights 2.2 GB
Weights 2.2 GB
KV cache @ 8K 0.81 GB
Runtime overhead 0.6 GB
Free 92.4 GB of 96.0 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 7.2 GB | 8.6 GB | 256K | 62 | Reference | Long context |
| Q8_0 | 3.8 GB | 5.2 GB | 256K | 117 | −0.1% ppl | Long context |
| Q6_K | 2.9 GB | 4.4 GB | 256K | 152 | −0.4% ppl | Long context |
| Q5_K_M | 2.5 GB | 4.0 GB | 256K | 176 | −0.8% ppl | Long context |
| Q4_K_M | 2.2 GB | 3.6 GB | 256K | 207 | −1.9% ppl | Recommended |
| Q3_K_M | 1.8 GB | 3.2 GB | 256K | 255 | −5.4% ppl | Long context |
| Q2_K | 1.5 GB | 2.9 GB | 256K | 298 | −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.
How to run it
$ pip install mlx-lm $ mlx_lm.generate --model mlx-community/Ministral-3-3B-Instruct-2512-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
01Download is 2.2 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02macOS caps what the GPU may wire down at about 96.0 GB of 128 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03There is room to go to the model's full 256K context on this card.
Related models on an M1 Ultra · 128 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Ministral 3 8B 8.92B · same family |
Q4_K_M · 6.7 GB | 89 | Runs great |
| Ministral 3 14B 13.9B · same family |
Q4_K_M · 9.7 GB | 57 | Runs great |
| Phi-4-mini 3.8B 3.84B · similar size |
Q4_K_M · 3.8 GB | 207 | Runs great |
| Qwen3 4B 4.02B · similar size |
Q4_K_M · 4.0 GB | 198 | Runs great |
| Gemma 3 4B 4.3B · similar size |
Q4_K_M · 3.3 GB | 185 | Runs great |
| Granite 4.1 3B 3.4B · similar size |
Q4_K_M · 3.1 GB | 234 | Runs great |
| Llama 3.2 3B Instruct 3.21B · similar size |
Q4_K_M · 3.3 GB | 248 | Runs great |
Ministral 3 3B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 3060 Laptop 5.3 GB usable · 336 GB/s |
3.6 GB | 94 | Runs great |
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
3.6 GB | 72 | Runs great |
| M3 · 8 GB 5.4 GB usable · 100 GB/s |
3.6 GB | 26 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
3.6 GB | 101 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
3.6 GB | 31 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
3.6 GB | 282 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
3.6 GB | 268 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
3.6 GB | 103 | Runs great |