selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

nvidia logo

Can the RTX 3090 run NLD-Uni?

NLD-Uni·18.3B·GeForce RTX 3090·24 GB VRAM

Saved in this browser, used on every model page.
Yes

Yes. The RTX 3090 runs NLD-Uni fully in VRAM at Q8_0 (about 21 GB of 24 GB), at roughly 27 tokens/s.

best quant
Q8_0
needs
21 GB
usable
24 GB
est. speed
~27 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the NLD-Uni page →

Every quantisation of NLD-Uni on the RTX 3090

QuantQualityMemoryFitSpeed
Q2_K Heavy loss7.4 GBfits~86 tok/s
Q3_K_M Noticeable loss10 GBfits~58 tok/s
Q4_K_M Small loss12 GBfits~46 tok/s
Q5_K_M Near-lossless14 GBfits~40 tok/s
Q6_K Near-lossless16 GBfits~34 tok/s
Q8_0 pickLossless21 GBfits~27 tok/s
FP16 / BF16 Lossless37 GBoffload~2.3 tok/s

Speed is a bandwidth-based estimate for generating text (936 GB/s); prompt processing and long contexts are slower.

Measured speed on the RTX 3090

No community reports for this pair yet.

Report your own speed →

Omni models that fit the RTX 3090 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
17.5BQ8_0≈20 GBFits in memory~28 tok/sCommercial OK
12BQ8_0≈16 GBFits in memory~41 tok/sCommercial OK
24.3BQ6_K≈21 GBFits in memory~26 tok/sCommercial OK
ByteDance-Seed logoBAGEL-7B-MoTByteDance-Seed
14.7BQ8_0≈17 GBFits in memory~33 tok/sCommercial OK
10.7BQ8_0≈8.9 GBFits in memory~45 tok/sCommercial OK
35.3BA3BQ4_K_M≈19 GBFits in memory~283 tok/sCommercial OK

Other GPUs that run NLD-Uni

Frequently asked questions

Can the RTX 3090 run NLD-Uni?
Yes. The RTX 3090 runs NLD-Uni fully in VRAM at Q8_0 (about 21 GB of 24 GB), at roughly 27 tokens/s.
How fast does NLD-Uni run on the RTX 3090?
An estimate from memory bandwidth gives about 27 tokens/s at Q8_0.
Which quantisation of NLD-Uni should I use on the RTX 3090?
Q8_0: the largest one that fits. Expected quality: lossless compared with the full-precision weights.

Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.