Text model · Mistral
Ministral 3 8B: RAM and VRAM requirements
Ministral 3 8B needs about 6.3 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~4.84 GB to download; KV cache and overhead add the rest), or about 9.9 GB at Q8_0. The lightest hardware that runs it is Nvidia GeForce RTX 3060 Ti (8GB).
Mistral family · 8B params · released Dec 2025 · 1.4M Ollama pulls.
Shopping for hardware? See what runs Ministral 3 8B →
Q4_K_M and Q8_0 are GGUF download (file) sizes. Memory @ Q4 includes the KV cache and overhead, so it runs larger than the file on disk.
Will it run on your device?
Ministral 3 8B runs on 35 of 43 tracked devices at Q4_K_M.
Memory breakdown
How context length changes it
Longer context grows the KV cache quickly: Ministral 3 8B needs ~6.3 GB at 4k but ~27.3 GB at 128k, which can push it past a device that fits it at a short context.
Speed drops too: every token re-reads the KV cache, so at 128k context Ministral 3 8B generates at roughly ~18% of its short-context speed. How this is estimated.
Quantization sizes
| Quantization | Size on disk |
|---|---|
| Q2_K | 3.4 GB est |
| Q3_K_M | 3.9 GB est |
| Q4_K_M (default) | 4.84 GB |
| Q5_K_M | 5.7 GB est |
| Q6_K | 6.6 GB est |
| Q8_0 | 8.41 GB |
| FP16 | 17.85 GB |
Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.
Run it
ollama run ministral-3:8b llama-cli -hf mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M lms get mistralai/Ministral-3-8B-Instruct-2512-GGUF Which devices can run Ministral 3 8B?
NVIDIA GPUs
- Nvidia GeForce RTX 2060 (6GB) No
- Nvidia GeForce RTX 3060 Ti (8GB) Tight
- Nvidia GeForce GTX 1070 (8GB) Tight
- Nvidia GeForce RTX 3060 (12GB) Yes
- Nvidia GeForce RTX 4070 (12GB) Yes
- Nvidia GeForce RTX 4060 Ti (16GB) Yes
- Nvidia GeForce RTX 4080 (16GB) Yes
- Nvidia GeForce RTX 4090 (24GB) Yes
- Nvidia GeForce RTX 3090 (24GB) Yes
- Nvidia GeForce RTX 5090 (32GB) Yes
Apple Silicon Macs
- Apple M1 (8GB) No
- Apple M2 (16GB) Yes
- Apple M4 (16GB) Yes
- Apple M5 (16GB) Yes
- Apple M3 Pro (18GB) Yes
- Apple M4 (24GB) Yes
- Apple M4 Pro (24GB) Yes
- Apple M5 (32GB) Yes
- Apple M4 Pro (48GB) Yes
- Apple M5 Pro (48GB) Yes
- Apple M4 Max (64GB) Yes
- Apple M4 Max (128GB) Yes
- Apple M5 Max (128GB) Yes
- Apple M3 Ultra (256GB) Yes
RAM-only laptops
iPhone & iPad
Android
Same job, different size
Pick by what fits your memory: step down to free up VRAM, or step up if you have headroom.
Similar models
Head-to-head
- Ministral 3 8B vs Ministral 3 3B
- Ministral 3 8B vs Mistral 7B
- Ministral 3 8B vs Mistral Nemo 12B
- Ministral 3 8B vs Ministral 3 14B
- Ministral 3 8B vs Mistral Small 3 24B
- Ministral 3 8B vs Mistral Small 3.1 24B
- Ministral 3 8B vs Magistral Small
- Ministral 3 8B vs Devstral Small
- Ministral 3 8B vs Devstral Small 2 24B
- Ministral 3 8B vs Mixtral 8x7B
- Ministral 3 8B vs Devstral 2 123B
FAQ
How much VRAM or RAM does Ministral 3 8B need?
At Q4_K_M, Ministral 3 8B needs about 6.3 GB (weights ~4.84 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~9.9 GB.
What is the Q4_K_M GGUF file size of Ministral 3 8B?
The Q4_K_M GGUF file is about 4.84 GB to download, and the Q8_0 GGUF is about 8.41 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~6.3 GB of memory at Q4_K_M.
Can Ministral 3 8B run on a laptop?
Yes, Ministral 3 8B fits on a 16 GB machine at Q4_K_M and runs on Apple Silicon or a 12 GB+ GPU comfortably.
Can I use Ministral 3 8B commercially?
Yes. Ministral 3 8B is licensed Apache-2.0, which permits commercial use.
Understand the numbers
Short guides to the ideas behind Ministral 3 8B's memory and quant figures.
Mid size of Mistral's edge family: dense 8B with vision, 256K context, Apache-2.0. Sizes from Mistral's own GGUF repo.
Sources
Last validated 2026-09-07. Memory figures are estimates. See methodology.