Can I Run Devstral on NVIDIA GeForce RTX 4080?
Written by Jakub Rusinowski · Last updated September 11, 2026
Yes, but it's tight — Devstral 2 22B at Q4_K_M needs 15.7 GB at 8K context (13.3 GB weights + 2.4 GB KV cache/overhead), leaving ~0.3 GB of the NVIDIA GeForce RTX 4080's 16 GB, at ~43 tok/s (est.), with room for up to 8K context.
See what else this hardware can run →
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.
NVIDIA GeForce RTX 4080 Specs
| VRAM | 16 GB |
| Memory Bandwidth | 717 GB/s |
Devstral 2 22B on the NVIDIA GeForce RTX 4080: VRAM by quantization
| Quant | VRAM needed | Fits 16 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 46.4 GB | ✗ No | — | — |
| Q8_0 | 25.8 GB | ✗ No | — | — |
| Q6_K | 20.5 GB | ✗ No | — | — |
| Q5_K_M | 18 GB | ✗ No | — | — |
| Q4_K_M | 15.7 GB | ✓ Yes | 8K | — |
| Q3_K_M | 11.8 GB | ✓ Yes | 16K | — |
| Q2_K | 9.6 GB | ✓ Yes | 32K | — |
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 NVIDIA GeForce RTX 4080: 8K 15.7 GB · 32K 20.5 GB ✗ · 125K 39.2 GB ✗. Past 32K 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 2 22B on 16 GB of system RAM, CPU only: runs, but it is tight.
Devstral Sizes That Fit the NVIDIA GeForce RTX 4080 (at 8K context)
| Devstral 2 22B | Q4_K_M · 15.7 GB at 8K context · ~43 tok/s (est.) |
At 2 hrs/day, buying (~$1,199) beats renting at $0.34/hr after about 4.9 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
Can I run Devstral on the NVIDIA GeForce RTX 4080?
Yes, but it's tight — Devstral 2 22B at Q4_K_M needs 15.7 GB at 8K context (13.3 GB weights + 2.4 GB KV cache/overhead), leaving ~0.3 GB of the NVIDIA GeForce RTX 4080's 16 GB, at ~43 tok/s (est.), with room for up to 8K context.
What's the best Devstral size for the NVIDIA GeForce RTX 4080?
Devstral 2 22B at Q4_K_M quantization needs 15.7 GB at 8K context (13.3 GB weights + 2.4 GB KV cache/overhead), estimated ~43 tokens/sec, up to 8K context.
Every Devstral size on the NVIDIA GeForce RTX 4080
| Size | VRAM at 8K | Verdict | Speed |
|---|---|---|---|
| Devstral-2 123B | 77.9 GB | Does not fit | — |
| Devstral Small 2505 24B | 16.6 GB | Runs at Q3_K_M | — |
| Devstral Small 2 24B | 16.6 GB | Runs at Q3_K_M | — |
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 4070 Ti Super
Popular Models on the NVIDIA GeForce RTX 4080
- DeepSeek R1 on NVIDIA GeForce RTX 4080
- Qwen 3 on NVIDIA GeForce RTX 4080
- Qwen 2.5 Family on NVIDIA GeForce RTX 4080
VRAM Tier
Troubleshooting
- CUDA out of memory — why it happens and how to fix it
- Which GGUF quant should I download? (Q4 vs Q5 vs Q8)
Buying Guide
← Can I Run It? | Devstral Model Page | NVIDIA GeForce RTX 4080 GPU Page | VRAM calculator | Check Your Hardware