← AI Hashrate

Can RTX 4090D 24GB (China) run Mixtral-8x7B-Instruct-v0.1?

NVIDIA · 24 GB GDDR6X · 1008 GB/s bandwidth · Mistral · 46.7B (active 12.9B) · MoE · model ctx up to 32K

No — Mixtral-8x7B-Instruct-v0.1 at Q4 needs ≈ 27.98 GB even at 4K context, beyond the RTX 4090D 24GB (China)'s 24 GB GDDR6X. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 95.5 tok/s (estimated, batch 1). FP16 needs ≈ 96.98 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)
Q44K27.98 GBNo104.5 est.
Q48K default29.27 GBNo95.5 est.
Q432K37.01 GBNo59.7 est.
FP164K95.69 GBNo2.5 est.
FP168K default96.98 GBNo
FP1632K104.72 GBNo

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 4090D 24GB (China) VRAM
Q425.69 GB2.58 GB1 GB29.27 GB24 GB
FP1693.4 GB2.58 GB1 GB96.98 GB24 GB

Other GPUs that run Mixtral-8x7B-Instruct-v0.1

All GPUs for Mixtral-8x7B-Instruct-v0.1 →

Other models for the RTX 4090D 24GB (China)

All models on the RTX 4090D 24GB (China) →