Can MI300X 192GB run Devstral-Small-2507?

AMD · 192 GB HBM3 · 5300 GB/s bandwidth · Mistral · 23.6B · model ctx up to 128K

Yes — the MI300X 192GB (192 GB HBM3) can run Devstral-Small-2507. At Q4 with the default 8K context it needs ≈ 18.7 GB VRAM (weights 12.98 GB + KV cache 4.72 GB + 1 GB runtime overhead), which fits within 192 GB. Decode at Q4/8K: ≈ 142.9 tok/s (estimated, batch 1). FP16 (≈ 52.92 GB) also fits, at ≈ 39.3 tok/s (estimated). 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	Yes	142.9 est.
Q4	8K default	18.7 GB	Yes	142.9 est.
Q4	32K	32.86 GB	Yes	142.9 est.
FP16	4K	50.56 GB	Yes	39.3 est.
FP16	8K default	52.92 GB	Yes	39.3 est.
FP16	32K	67.08 GB	Yes	39.3 est.

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	MI300X 192GB VRAM
Q4	12.98 GB	4.72 GB	1 GB	18.7 GB	192 GB
FP16	47.2 GB	4.72 GB	1 GB	52.92 GB	192 GB

Other GPUs that run Devstral-Small-2507

• B200 192GB SXM — ≈215.7 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.
• RTX 4090D 24GB (China) — ≈27.2 tok/s Q4 est.

All GPUs for Devstral-Small-2507 →

Other models for the MI300X 192GB

• Qwen3-0.6B — ≈4215.9 tok/s Q4 est.
• gemma-3-1b-it — ≈3372.7 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈2810.6 tok/s Q4 est.
• Qwen3-1.7B — ≈1686.4 tok/s Q4 est.
• Qwen3-30B-A3B — ≈1124.2 tok/s Q4 est.
• Qwen3-Coder-30B-A3B-Instruct — ≈1124.2 tok/s Q4 est.
• GLM-4.7-Flash — ≈1124.2 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈1124.2 tok/s Q4 est.

All models on the MI300X 192GB →