Can I Run Devstral on AMD Radeon RX 9070?
作者： Jakub Rusinowski · 最后更新： 2026年9月11日
Yes, but it's tight — Devstral Small 2505 24B at Q4_K_M needs 14.5 GB of the AMD Radeon RX 9070's 16 GB, leaving only ~1.5 GB, ~27 tok/s (est.) with room for up to 4K context.
See what else this hardware can run →
或在 Vast.ai 比较，低至 $0.35/小时 (typical low · varies)
作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。
AMD Radeon RX 9070 Specs
| VRAM | 16 GB |
| Memory Bandwidth | 640 GB/s |
Devstral Small 2505 24B on the AMD Radeon RX 9070: VRAM by quantization
| Quant | VRAM needed | Fits 16 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 49.5 GB | ✗ No | — | — |
| Q8_0 | 27 GB | ✗ No | — | — |
| Q6_K | 21.2 GB | ✗ No | — | — |
| Q5_K_M | 18.5 GB | ✗ No | — | — |
| Q4_K_M | 16 GB | ✓ Yes | 4K | — |
| Q3_K_M | 11.7 GB | ✓ Yes | 16K | — |
| Q2_K | 9.4 GB | ✓ Yes | 32K | — |
Assumes a 4K-token context with an f16 KV cache. 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 16.6 GB ✗ · 32K 20.7 GB ✗ · 128K 36.8 GB ✗. Past 8K it no longer fits 16 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
No compatible GPU? Devstral Small 2505 24B on 24 GB of system RAM, CPU only: runs comfortably.
Devstral Sizes That Fit the AMD Radeon RX 9070
| Devstral Small 2505 24B | Q4_K_M · 14.5 GB · ~27 tok/s (est.) |
| Devstral 2 22B | Q4_K_M · 13.3 GB · ~29 tok/s (est.) |
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.
FAQ
Is the AMD Radeon RX 9070 enough to run Devstral locally?
Yes, but it's tight — Devstral Small 2505 24B at Q4_K_M needs 14.5 GB of the AMD Radeon RX 9070's 16 GB, leaving only ~1.5 GB, ~27 tok/s (est.) with room for up to 4K context.
What's the best Devstral size for the AMD Radeon RX 9070?
Devstral Small 2505 24B at Q4_K_M quantization (14.5 GB), estimated ~27 tokens/sec, up to 4K context.
Every Devstral size on the AMD Radeon RX 9070
| Size | VRAM | Verdict | Speed |
|---|---|---|---|
| Devstral-2 123B | 74.3 GB | Does not fit | — |
| Devstral Small 2505 24B | 14.5 GB | Runs | ~27 tok/s |
| Devstral Small 2 24B | 14.5 GB | Runs at Q3_K_M | — |
| Devstral 2 22B | 13.3 GB | Runs | ~29 tok/s |
Devstral on Other GPUs
- Devstral on NVIDIA GeForce RTX 5080
- Devstral on NVIDIA GeForce RTX 5070 Ti
- Devstral on NVIDIA GeForce RTX 5060 Ti 16GB
- Devstral on NVIDIA GeForce RTX 4080 Super
- Devstral on NVIDIA GeForce RTX 4080
Popular Models on the AMD Radeon RX 9070
VRAM Tier
Troubleshooting
- Ollama: "model requires more system memory than is available"
- Which GGUF quant should I download? (Q4 vs Q5 vs Q8)
Buying Guide
← Can I Run It? | Devstral Model Page | AMD Radeon RX 9070 GPU Page | Check Your Hardware