Written by Jakub Rusinowski · Last updated September 11, 2026
Yes, but it's tight — Devstral Small 2505 24B at Q4_K_M needs 14.5 GB of the NVIDIA GeForce RTX 4080 Super's 16 GB, leaving only ~1.5 GB, ~41 tok/s (est.) with room for up to 4K 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.
| VRAM | 16 GB |
| Memory Bandwidth | 736 GB/s |
| 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 NVIDIA GeForce RTX 4080 Super: 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 16 GB of system RAM, CPU only: runs, but it is tight.
| Devstral Small 2505 24B | Q4_K_M · 14.5 GB · ~41 tok/s (est.) |
| Devstral-2 22B (Unverified Listing) | Q4_K_M · 13.3 GB · ~44 tok/s (est.) |
At 2 hrs/day, buying (~$999) beats renting at $0.34/hr after about 4.1 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.
Yes, but it's tight — Devstral Small 2505 24B at Q4_K_M needs 14.5 GB of the NVIDIA GeForce RTX 4080 Super's 16 GB, leaving only ~1.5 GB, ~41 tok/s (est.) with room for up to 4K context.
Devstral Small 2505 24B at Q4_K_M quantization (14.5 GB), estimated ~41 tokens/sec, up to 4K context.
| Size | VRAM | Verdict | Speed |
|---|---|---|---|
| Devstral-2 123B | 74.3 GB | Does not fit | — |
| Devstral Small 2505 24B | 14.5 GB | Runs | ~41 tok/s |
| Devstral Small 2 24B | 14.5 GB | Runs at Q3_K_M | — |
| Devstral-2 22B (Unverified Listing) | 13.3 GB | Runs | ~44 tok/s |
← Can I Run It? | Devstral Model Page | NVIDIA GeForce RTX 4080 Super GPU Page | Check Your Hardware