Strata on the NVIDIA RTX 3090
llamaperf has 11 Strata reports on the NVIDIA RTX 3090, none of them a plain single-card run with a model size and quant, so there is no median to quote. The reports are listed below with how each one ran.
11 Strata reports on the NVIDIA RTX 3090
Newest first. A run on several cards, with speculative decoding, with part of the model in system RAM or with batched requests says so, since each describes a different setup.
- Qwen3.8 125B · 6B active · IQ3_XXSPP 1325.0 t/s(speculative decoding, part in system RAM)
- GLM-5.3 320B · 18B active · GSQ-RCO 3.5-bit19.1 t/s(part in system RAM)
- Qwen3.8 125B · 6B active · IQ4_XS100.0 t/s(2 cards, part in system RAM)
- Qwen3.8 125B · 6B active · Q6_K_XL43.9 t/s(2 cards, speculative decoding, part in system RAM)
- Qwen3.8 125B · 6B active · UD-Q4_K_XL97.0 t/s(2 cards, speculative decoding, part in system RAM)
- GLM-5.3 320B · 18B active · UD-Q4_K_XL19.8 t/s(part in system RAM)
- Qwen3.8 125B · 6B active · IQ3_S116.0 t/s(2 cards, speculative decoding)
- Qwen3.8 125B · 6B active · UD-Q4_K_XLPP 1700.0 t/s(part in system RAM)
- Qwen3.8 125B · 6B active · Q834.0 t/s(2 cards, speculative decoding, part in system RAM)
- Qwen3.8 125B · 6B active · IQ3_S167.0 t/s(2 cards)
- Qwen3.8 125B · 6B active · UD-Q3_K_XLPP 1650.0 t/s(speculative decoding, part in system RAM)
Frequently asked
How fast is Strata on the NVIDIA RTX 3090?
llamaperf has 11 Strata reports on the NVIDIA RTX 3090, none of them a plain single-card run with a model size and quant, so there is no median to quote. The reports are listed below with how each one ran.