Ministral 8B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
The best lightweight Mistral model. Outstanding reasoning scores for 8B size. Works on 6 GB VRAM cards (RTX 3060, RTX 4060, RX 7600). Very fast at 60–90 tokens/sec.
Ministral 8B needs about 6 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 4.6 GB | ~153 tok/s | Fits | |
| Q3_K_M 3.41 bpw | 5.4 GB | ~132 tok/s | Fits | |
| Q4_K_M 4.83 bpw | 6.9 GB | ~106 tok/s | Fits | |
| Q5_K_M 5.67 bpw | 7.7 GB | ~95 tok/s | Fits | |
| Q6_K 6.56 bpw | 8.6 GB | ~85 tok/s | Fits | |
| Q8_0 8.50 bpw | 10.5 GB | ~70 tok/s | Fits | |
| F16 16.00 bpw | 18 GB | ~41 tok/s | Fits |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Ministral 8B VRAM calculator →
Get Ministral 8B running
The cheapest catalogued GPU that runs Ministral 8B is the Intel Arc B570 (10 GB).
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run Ministral 8B
Install Ollama, then run:
ollama run ministral:8bSpecifications
Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.
- Parameters
- 8 Billion
- Context window
- 32,768
- Architecture
- Dense, Decoder-only
- Provider
- Mistral AI
- Licence
- Mistral Research
- Practical deployment
- Laptop
- Specified at
- Q4_K_M
- System RAM
- 16 GB
- Record updated
- 2024-10-16
Research / non-commercial only — this licence does NOT permit shipping a commercial product.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Can I run Ministral 8B on my GPU?
- Ministral 8B on AMD Radeon RX 9060 XT 8GB
- Ministral 8B on Intel Arc B570
- Ministral 8B on Intel Arc B580
- Ministral 8B on NVIDIA GeForce RTX 3060 (12GB)
- Ministral 8B on NVIDIA GeForce RTX 3070
- Ministral 8B on NVIDIA GeForce RTX 3070 Ti
- Ministral 8B on NVIDIA GeForce RTX 3080 (10GB)
- Ministral 8B on NVIDIA GeForce RTX 4060
- Ministral 8B on NVIDIA GeForce RTX 4070
- Ministral 8B on NVIDIA GeForce RTX 4070 Super
- Ministral 8B on NVIDIA GeForce RTX 4070 Ti
- Ministral 8B on NVIDIA GeForce RTX 5060
- Ministral 8B on NVIDIA GeForce RTX 5060 Ti 8GB
- Ministral 8B on NVIDIA GeForce RTX 5070
Other Ministral sizes
Ministral 8B — frequently asked questions
How much VRAM does Ministral 8B need?
About 6 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Ministral 8B run on an RTX 4090 (24 GB)?
Yes. Ministral 8B needs about 6 GB at Q4_K_M, inside a 24 GB card, at an estimated 106 tokens/sec.
How do I run Ministral 8B locally?
Install Ollama and run `ollama run ministral:8b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Ministral come in?
Ministral 3B (3 GB), Ministral 8B (6 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.