Can RX 7700 XT 12GB run Magistral-Small-2509?

AMD · 12 GB GDDR6 · 432 GB/s bandwidth · Mistral · 24.0B · model ctx up to 128K

No — Magistral-Small-2509 at Q4 needs ≈ 16.6 GB even at 4K context, beyond the RX 7700 XT 12GB's 12 GB GDDR6. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 13.1 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	No	17.1 est.
Q4	8K default	19.0 GB	No	13.1 est.
Q4	32K	33.4 GB	No	4.2 est.
FP16	4K	51.4 GB	No	—
FP16	8K default	53.8 GB	No	—
FP16	32K	68.2 GB	No	—

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).

VRAM breakdown at 8K context

Quant	Weights	KV cache	Overhead	Total needed	RX 7700 XT 12GB VRAM
Q4	13.2 GB	4.8 GB	1 GB	19.0 GB	12 GB
FP16	48.0 GB	4.8 GB	1 GB	53.8 GB	12 GB

Other GPUs that run Magistral-Small-2509

• B200 192GB SXM — ≈212.1 tok/s Q4 est.
• MI300X 192GB — ≈140.5 tok/s Q4 est.
• H200 141GB SXM5 — ≈127.3 tok/s Q4 est.
• H100 80GB SXM5 — ≈88.8 tok/s Q4 est.
• Gaudi 3 128GB — ≈86.9 tok/s Q4 est.
• A100 80GB SXM4 — ≈54.1 tok/s Q4 est.
• RTX 5090 32GB — ≈47.5 tok/s Q4 est.
• RTX 4090 24GB — ≈26.7 tok/s Q4 est.

All GPUs for Magistral-Small-2509 →

Other models for the RX 7700 XT 12GB

• Qwen3-0.6B — ≈343.6 tok/s Q4 est.
• gemma-3-1b-it — ≈274.9 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈229.1 tok/s Q4 est.
• Qwen3-1.7B — ≈137.5 tok/s Q4 est.
• Llama-3.2-3B-Instruct — ≈85.9 tok/s Q4 est.
• Phi-4-mini-instruct — ≈72.3 tok/s Q4 est.
• Phi-4-mini-reasoning — ≈72.3 tok/s Q4 est.
• gemma-3-4b-it — ≈70.5 tok/s Q4 est.

All models on the RX 7700 XT 12GB →