Can I Run Ministral 3 8B on AMD Radeon RX 9070?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 6 września 2026
Yes. Ministral 3 8B needs 6.8 GB at 8K context (4.8 GB weights + 2 GB KV cache/overhead) at Q4_K_M and the AMD Radeon RX 9070 has 16 GB, leaving about 9.2 GB of headroom, at roughly 64 tok/s (estimated) with room for up to 64K of context.
See what else this hardware can run →
The numbers
| Model | Ministral 3 8B |
| Parameters | 8B |
| Quantization | Q4_K_M |
| VRAM needed (8K context) | 6.8 GB |
| AMD Radeon RX 9070 VRAM | 16 GB |
| Verdict | Runs |
| Max context | 64K |
| Estimated speed | ~64 tok/s |
Ministral 3 8B on the AMD Radeon RX 9070: VRAM by quantization
| Quant | VRAM needed | Fits 16 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 17.9 GB | ✗ No | — | — |
| Q8_0 | 10.4 GB | ✓ Yes | 32K | — |
| Q6_K | 8.5 GB | ✓ Yes | 32K | — |
| Q5_K_M | 7.6 GB | ✓ Yes | 64K | — |
| Q4_K_M | 6.8 GB | ✓ Yes | 64K | — |
| Q3_K_M | 5.4 GB | ✓ Yes | 64K | — |
| Q2_K | 4.6 GB | ✓ Yes | 64K | — |
Assumes an 8K-token context with an f16 KV cache, on an estimated architecture — this model publishes no config we can read. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 16 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the AMD Radeon RX 9070: 8K 6.8 GB · 32K 10.2 GB · 128K 23.9 GB ✗. Past 128K it no longer fits 16 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
What to do next
Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.
No compatible GPU? Ministral 3 on 8 GB of system RAM, CPU only: runs comfortably.
Running Ministral 3 8B on this card:
At 2 hrs/day, buying (~$549) beats renting at $0.34/hr after about 2.2 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
Other Ministral 3 sizes on the AMD Radeon RX 9070
- Ministral 3 14B — runs (10.6 GB)
- Ministral 3 3B — runs (3.5 GB)
Ministral 3 8B on nearby hardware
- Intel Arc B580 (12 GB) — runs
- AMD Radeon RX 7900 XT (20 GB) — runs
All Ministral 3 sizes on the AMD Radeon RX 9070 | Ministral 3 8B model page | AMD Radeon RX 9070 GPU page | VRAM calculator | Check your hardware