← AI Hashrate

Can L40S 48GB run Ornith-1.0-35B?

NVIDIA · 48 GB GDDR6 · 864 GB/s bandwidth · DeepReinforce · 35.0B (active 3.0B) · MoE · model ctx up to 256K

Yes — the L40S 48GB (48 GB GDDR6) can run Ornith-1.0-35B. At Q4 with the default 8K context it needs ≈ 20.85 GB VRAM (weights 19.25 GB + KV cache 0.6 GB + 1 GB runtime overhead), which fits within 48 GB. Decode at Q4/8K: ≈ 183.3 tok/s (estimated, batch 1). FP16 needs ≈ 71.6 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)
Q44K20.55 GBYes183.3 est.
Q48K default20.85 GBYes183.3 est.
Q432K22.65 GBYes183.3 est.
FP164K71.3 GBNo65.3 est.
FP168K default71.6 GBNo64.7 est.
FP1632K73.4 GBNo61.6 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 neededL40S 48GB VRAM
Q419.25 GB0.6 GB1 GB20.85 GB48 GB
FP1670.0 GB0.6 GB1 GB71.6 GB48 GB

Other GPUs that run Ornith-1.0-35B

All GPUs for Ornith-1.0-35B →

Other models for the L40S 48GB

All models on the L40S 48GB →