NVIDIA · 24 GB GDDR6X · 936 GB/s bandwidth ·
Mistral · 24.0B · model ctx up to 128K
Yes — the RTX 3090 24GB (24 GB GDDR6X) can run Magistral-Small-2509. At Q4 with the default 8K context it needs ≈ 19.0 GB VRAM (weights 13.2 GB + KV cache 4.8 GB + 1 GB runtime overhead), which fits within 24 GB. Decode at Q4/8K: ≈ 24.8 tok/s (estimated, batch 1). FP16 needs ≈ 53.8 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.
Fit & speed by quant and context
Quant
Context
VRAM needed
Fits?
tok/s (decode)
Q4
4K
16.6 GB
Yes
24.8est.
Q4
8K default
19.0 GB
Yes
24.8est.
Q4
32K
33.4 GB
No
36.6est.
FP16
4K
51.4 GB
No
4.3est.
FP16
8K default
53.8 GB
No
3.9est.
FP16
32K
68.2 GB
No
2.4est.
Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured
anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s
means the model is far beyond this card (offload-only territory).