← AI Hashrate

Can Arc B580 12GB run Mistral-7B-Instruct-v0.3?

Intel · 12 GB GDDR6 · 456 GB/s bandwidth · Mistral · 7.2B · model ctx up to 32K

Yes — the Arc B580 12GB (12 GB GDDR6) can run Mistral-7B-Instruct-v0.3. At Q4 with the default 8K context it needs ≈ 6.4 GB VRAM (weights 3.96 GB + KV cache 1.44 GB + 1 GB runtime overhead), which fits within 12 GB. Decode at Q4/8K: ≈ 40.3 tok/s (estimated, batch 1). FP16 needs ≈ 16.84 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

QuantContextVRAM neededFits?tok/s (decode)
Q44K5.68 GBYes40.3 est.
Q48K default6.4 GBYes40.3 est.
Q432K10.72 GBYes40.3 est.
FP164K16.12 GBNo17.5 est.
FP168K default16.84 GBNo16.1 est.
FP1632K21.16 GBNo10.2 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

QuantWeightsKV cacheOverheadTotal neededArc B580 12GB VRAM
Q43.96 GB1.44 GB1 GB6.4 GB12 GB
FP1614.4 GB1.44 GB1 GB16.84 GB12 GB

Other GPUs that run Mistral-7B-Instruct-v0.3

All GPUs for Mistral-7B-Instruct-v0.3 →

Other models for the Arc B580 12GB

All models on the Arc B580 12GB →