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 A4000 run NLD-Uni?

NLD-Uni·18.3B·RTX A4000·16 GB VRAM

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

Yes. The RTX A4000 runs NLD-Uni fully in VRAM at Q5_K_M (about 14 GB of 16 GB), at roughly 19 tokens/s.

best quant
Q5_K_M
needs
14 GB
usable
16 GB
est. speed
~19 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 A4000

QuantQualityMemoryFitSpeed
Q2_K Heavy loss7.4 GBfits~41 tok/s
Q3_K_M Noticeable loss10 GBfits~28 tok/s
Q4_K_M Small loss12 GBfits~22 tok/s
Q5_K_M pickNear-lossless14 GBfits~19 tok/s
Q6_K Near-lossless16 GBoffload~15 tok/s
Q8_0 Lossless21 GBoffload~5.2 tok/s
FP16 / BF16 Lossless37 GBoffload~1.4 tok/s

Speed is a bandwidth-based estimate for generating text (448 GB/s); prompt processing and long contexts are slower.

Measured speed on the RTX A4000

No community reports for this pair yet.

Report your own speed →

Omni models that fit the RTX A4000 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
17.5BQ6_K≈9.3 GBFits in memory~17 tok/sCommercial OK
12BQ6_K≈13 GBFits in memory~25 tok/sCommercial OK
ByteDance-Seed logoBAGEL-7B-MoTByteDance-Seed
14.7BQ6_K≈13 GBFits in memory~20 tok/sCommercial OK
10.7BQ8_0≈8.9 GBFits in memory~22 tok/sCommercial OK
HiDream-ai logoHiDream-E1-FullHiDream-ai
17.1BQ5_K_M≈15 GBFits in memory~20 tok/sCommercial OK
12BQ6_K≈13 GBFits in memory~25 tok/sCommercial OK

Other GPUs that run NLD-Uni

Frequently asked questions

Can the RTX A4000 run NLD-Uni?
Yes. The RTX A4000 runs NLD-Uni fully in VRAM at Q5_K_M (about 14 GB of 16 GB), at roughly 19 tokens/s.
How fast does NLD-Uni run on the RTX A4000?
An estimate from memory bandwidth gives about 19 tokens/s at Q5_K_M.
Which quantisation of NLD-Uni should I use on the RTX A4000?
Q5_K_M: the largest one that fits. Expected quality: near-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.