Can RX 9070 XT 16GB run Mistral-Small-3.2-24B-Instruct-2506?

AMD · 16 GB GDDR6 · 640 GB/s bandwidth · Mistral · 24.0B · model ctx up to 128K

No — Mistral-Small-3.2-24B-Instruct-2506 at Q4 needs ≈ 16.6 GB even at 4K context, beyond the RX 9070 XT 16GB's 16 GB GDDR6. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 34.4 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	45.0 est.
Q4	8K default	19.0 GB	No	34.4 est.
Q4	32K	33.4 GB	No	11.1 est.
FP16	4K	51.4 GB	No	1.3 est.
FP16	8K default	53.8 GB	No	1.2 est.
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 9070 XT 16GB VRAM
Q4	13.2 GB	4.8 GB	1 GB	19.0 GB	16 GB
FP16	48.0 GB	4.8 GB	1 GB	53.8 GB	16 GB

Other GPUs that run Mistral-Small-3.2-24B-Instruct-2506

• 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 Mistral-Small-3.2-24B-Instruct-2506 →

Other models for the RX 9070 XT 16GB

• Qwen3-0.6B — ≈509.1 tok/s Q4 est.
• gemma-3-1b-it — ≈407.3 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈339.4 tok/s Q4 est.
• Qwen3-1.7B — ≈203.6 tok/s Q4 est.
• gpt-oss-20b — ≈113.1 tok/s Q4 est.
• Phi-4-mini-instruct — ≈107.2 tok/s Q4 est.
• Phi-4-mini-reasoning — ≈107.2 tok/s Q4 est.
• gemma-3-4b-it — ≈104.4 tok/s Q4 est.

All models on the RX 9070 XT 16GB →