No — not on this device
Ministral 3 8B at Q4_K_M needs 6.7 GB against 5.4 GB usable, and the shortfall of 1.3 GB is more than 64 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.
Mistral's 8B with images in. Plain GQA, so budget more KV cache than Qwen3.5 9B at the same context.
Hardware requirements What hardware do I need to run Ministral 3 8B? →At Q4_K_M with an 8K context: a 10 GB GPU (Arc B570) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
Fits instead: Ministral 3 3B (3.6 GB)
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 16.6 GB | 18.3 GB | — | ~3.4 | Reference | 12.9 GB over |
| Q8_0 | 8.8 GB | 10.5 GB | — | ~6.3 | −0.1% ppl | 5.1 GB over |
| Q6_K | 6.8 GB | 8.5 GB | — | ~8.2 | −0.4% ppl | 3.1 GB over |
| Q5_K_M | 5.9 GB | 7.6 GB | — | ~9.5 | −0.8% ppl | 2.2 GB over |
| Q4_K_M | 5.0 GB | 6.7 GB | — | ~11 | −1.9% ppl | 1.3 GB over |
| Q3_K_M | 4.1 GB | 5.7 GB | 5K | ~14 | −5.4% ppl | 0.3 GB over |
| Q2_K | 3.5 GB | 5.1 GB | 9K | 16 | −15% ppl | Fits |
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-3-8B-Instruct-2512-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
Related models on an M3 · 8 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Ministral 3 14B 13.9B · same family |
Q4_K_M · 9.7 GB | — | Won't fit |
| Ministral 3 3B 3.85B · same family |
Q4_K_M · 3.6 GB | 26 | Runs great |
| Granite 4.1 8B 8.79B · similar size |
Q4_K_M · 6.8 GB | — | Won't fit |
| LFM2.5 8B-A1B 8.47B MoE · similar size |
Q4_K_M · 5.5 GB | — | Won't fit |
| Ornith 1.5 9B 9.41B · similar size |
Q4_K_M · 6.1 GB | — | Won't fit |
| Fara 7B 8.29B · similar size |
Q4_K_M · 5.7 GB | — | Won't fit |
| Qwen3.5 9B 9.65B · similar size |
Q4_K_M · 6.3 GB | — | Won't fit |
Ministral 3 8B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
6.7 GB | 31 | Tight fit |
| Arc B570 8.8 GB usable · 380 GB/s |
6.7 GB | 46 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
6.7 GB | 43 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
6.7 GB | 13 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
6.7 GB | 122 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
6.7 GB | 116 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
6.7 GB | 45 | Runs great |