Autor: Jakub Rusinowski · Ostatnia aktualizacja: 29 maja 2024
Yes, comfortably — you'll have ~3 GB of headroom running Codestral 22B at Q4_K_M (13 GB, ~74 tok/s (est.)) with room for up to 4K context.
Sprawdź cenę na Amazon — NVIDIA GeForce RTX 5080 16GB
| VRAM | 16 GB |
| Memory Bandwidth | 960 GB/s |
| Quant | VRAM needed | Fits 16 GB? | Max context |
|---|---|---|---|
| F16 | 46.1 GB | ✗ No | — |
| Q8_0 | 25.3 GB | ✗ No | — |
| Q6_K | 19.9 GB | ✗ No | — |
| Q5_K_M | 17.5 GB | ✗ No | — |
| Q4_K_M | 15.1 GB | ✓ Yes | 4K |
| Q3_K_M | 11.2 GB | ✓ Yes | 16K |
| Q2_K | 9 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. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
| Codestral 22B | Q4_K_M · 13 GB · ~74 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, comfortably — you'll have ~3 GB of headroom running Codestral 22B at Q4_K_M (13 GB, ~74 tok/s (est.)) with room for up to 4K context.
Codestral 22B at Q4_K_M quantization (13 GB), estimated ~74 tokens/sec, up to 4K context.
← Can I Run It? | Codestral Model Page | NVIDIA GeForce RTX 5080 GPU Page | Check Your Hardware