← AI Hashrate

Can RTX A6000 48GB run Mistral-7B-Instruct-v0.3?

NVIDIA · 48 GB GDDR6 · 768 GB/s bandwidth · Mistral · 7.2B · model ctx up to 32K

Yes — the RTX A6000 48GB (48 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 48 GB. Decode at Q4/8K: ≈ 67.9 tok/s (estimated, batch 1). FP16 (≈ 16.84 GB) also fits, at ≈ 18.7 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

QuantContextVRAM neededFits?tok/s (decode)
Q44K5.68 GBYes67.9 est.
Q48K default6.4 GBYes67.9 est.
Q432K10.72 GBYes67.9 est.
FP164K16.12 GBYes18.7 est.
FP168K default16.84 GBYes18.7 est.
FP1632K21.16 GBYes18.7 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 neededRTX A6000 48GB VRAM
Q43.96 GB1.44 GB1 GB6.4 GB48 GB
FP1614.4 GB1.44 GB1 GB16.84 GB48 GB

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

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

Other models for the RTX A6000 48GB

All models on the RTX A6000 48GB →