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.

internlm logo

Can the RTX 4070 run InternLumina-U2?

InternLumina-U2·16B·GeForce RTX 4070·12 GB VRAM

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

Yes, but only at Q3_K_M (about 9.6 GB of 12 GB), which costs noticeable quality, at roughly 35 tokens/s.

best quant
Q3_K_M
needs
9.6 GB
usable
12 GB
est. speed
~35 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the InternLumina-U2 page →

Every quantisation of InternLumina-U2 on the RTX 4070

QuantQualityMemoryFitSpeed
Q2_K Heavy loss7.1 GBfits~53 tok/s
Q3_K_M pickNoticeable loss9.6 GBfits~35 tok/s
Q4_K_M Small loss11 GBtight~29 tok/s
Q5_K_M Near-lossless13 GBoffload~15 tok/s
Q6_K Near-lossless15 GBoffload~8.7 tok/s
Q8_0 Lossless19 GBoffload~4.5 tok/s
FP16 / BF16 Lossless33 GBoffload~1.5 tok/s

Speed is a bandwidth-based estimate for generating text (504 GB/s); prompt processing and long contexts are slower.

Measured speed on the RTX 4070

No community reports for this pair yet.

Report your own speed →

Omni models that fit the RTX 4070 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
12BQ4_K_M≈10 GBFits in memory~38 tok/sCommercial OK
ByteDance-Seed logoBAGEL-7B-MoTByteDance-Seed
14.7BQ5_K_M≈11 GBFits in memory~27 tok/sCommercial OK
10.7BQ8_0≈8.9 GBFits in memory~24 tok/sCommercial OK
12BQ4_K_M≈11 GBFits in memory~38 tok/sCommercial OK
9.4BQ8_0≈10 GBFits in memory~28 tok/sCommercial OK
inclusionAI logoLLaDA2.0-UniinclusionAI
16.3BA1.5BQ4_K_M≈10 GBFits in memory~305 tok/sCommercial OK

Other GPUs that run InternLumina-U2

Frequently asked questions

Can the RTX 4070 run InternLumina-U2?
Yes, but only at Q3_K_M (about 9.6 GB of 12 GB), which costs noticeable quality, at roughly 35 tokens/s.
How fast does InternLumina-U2 run on the RTX 4070?
An estimate from memory bandwidth gives about 35 tokens/s at Q3_K_M.
Which quantisation of InternLumina-U2 should I use on the RTX 4070?
Q3_K_M: the largest one that fits. Expected quality: noticeable loss 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.