Can RX 9070 16GB run Devstral-Small-2507?

AMD · 16 GB GDDR6 · 640 GB/s bandwidth · Mistral · 23.6B · model ctx up to 128K

No — Devstral-Small-2507 at Q4 needs ≈ 16.34 GB even at 4K context, beyond the RX 9070 16GB's 16 GB GDDR6. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 36.1 tok/s (estimated, batch 1). FP16 needs ≈ 52.92 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	16.34 GB	No	47.3 est.
Q4	8K default	18.7 GB	No	36.1 est.
Q4	32K	32.86 GB	No	11.7 est.
FP16	4K	50.56 GB	No	1.4 est.
FP16	8K default	52.92 GB	No	1.2 est.
FP16	32K	67.08 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 16GB VRAM
Q4	12.98 GB	4.72 GB	1 GB	18.7 GB	16 GB
FP16	47.2 GB	4.72 GB	1 GB	52.92 GB	16 GB

Other GPUs that run Devstral-Small-2507

• B200 192GB SXM — ≈215.7 tok/s Q4 est.
• MI300X 192GB — ≈142.9 tok/s Q4 est.
• H200 141GB SXM5 — ≈129.4 tok/s Q4 est.
• H100 80GB SXM5 — ≈90.3 tok/s Q4 est.
• Gaudi 3 128GB — ≈88.3 tok/s Q4 est.
• A100 80GB SXM4 — ≈55.0 tok/s Q4 est.
• RTX 5090 32GB — ≈48.3 tok/s Q4 est.
• RTX 4090 24GB — ≈27.2 tok/s Q4 est.

All GPUs for Devstral-Small-2507 →

Other models for the RX 9070 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.
• Llama-3.2-3B-Instruct — ≈127.3 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.

All models on the RX 9070 16GB →