作者： Jakub Rusinowski · 最后更新： 2026年9月11日
Only with offload — Devstral spills onto CPU/system RAM on the Apple M1 (16 GB), so expect a large speed penalty.
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.
| VRAM | 16 GB unified memory |
| Memory Bandwidth | 68 GB/s |
| Quant | VRAM needed | Fits 16 GB? | Max context |
|---|---|---|---|
| F16 | 45.6 GB | ✗ No | — |
| Q8_0 | 25 GB | ✗ No | — |
| Q6_K | 19.6 GB | ✗ No | — |
| Q5_K_M | 17.2 GB | ✗ No | — |
| Q4_K_M | 14.9 GB | ✓ Yes | 8K |
| Q3_K_M | 11 GB | ✓ Yes | 16K |
| Q2_K | 8.8 GB | ✓ Yes | 32K |
VRAM needed assumes a 4K-token context with an f16 KV cache; “Max context” is the largest window that still fits in 16 GB of unified memory. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Every Devstral variant requires more VRAM than the Apple M1 provides (16 GB).
AMD Radeon RX 7900 XT (20 GB VRAM).
Devstral needs ~13 GB but this GPU has 16 GB. Rent a RTX 4090 (24 GB)-class GPU by the hour instead of buying one:
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.
Only with offload — Devstral spills onto CPU/system RAM on the Apple M1 (16 GB), so expect a large speed penalty.
The AMD Radeon RX 7900 XT (20 GB VRAM) is the cheapest upgrade that fits it.
| Size | VRAM | Verdict | Speed |
|---|---|---|---|
| Devstral-2 123B | 74.3 GB | Does not fit | — |
| Devstral Small 2505 24B | 14.5 GB | Runs at Q3_K_M | — |
| Devstral Small 2 24B | 14.5 GB | Runs at Q3_K_M | — |
| Devstral-2 22B (Unverified Listing) | 13.3 GB | Runs at Q3_K_M | — |
← Can I Run It? | Devstral Model Page | Apple M1 GPU Page | Check Your Hardware