Can the RTX A4000 run InternLumina-U2?
InternLumina-U2·16B·RTX A4000·16 GB VRAM
Yes. The RTX A4000 runs InternLumina-U2 fully in VRAM at Q6_K (about 15 GB of 16 GB), at roughly 19 tokens/s.
- best quant
- Q6_K
- needs
- 15 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 InternLumina-U2 page →
Every quantisation of InternLumina-U2 on the RTX A4000
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 7.1 GB | fits | ~47 tok/s |
| Q3_K_M | 9.6 GB | fits | ~32 tok/s |
| Q4_K_M | 11 GB | fits | ~25 tok/s |
| Q5_K_M | 13 GB | fits | ~22 tok/s |
| Q6_K pick | 15 GB | fits | ~19 tok/s |
| Q8_0 | 19 GB | offload | ~7.6 tok/s |
| FP16 / BF16 | 33 GB | offload | ~1.8 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 →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 12B | Q6_K | ≈13 GBFits in memory | ~25 tok/s | |
| 14.7B | Q6_K | ≈13 GBFits in memory | ~20 tok/s | |
| 17.5B | Q6_K | ≈9.3 GBFits in memory | ~17 tok/s | |
| 10.7B | Q8_0 | ≈8.9 GBFits in memory | ~22 tok/s | |
| 12B | Q6_K | ≈13 GBFits in memory | ~25 tok/s | |
| 9.4B | Q8_0 | ≈10 GBFits in memory | ~25 tok/s |
Other GPUs that run InternLumina-U2
Frequently asked questions
- Can the RTX A4000 run InternLumina-U2?
- Yes. The RTX A4000 runs InternLumina-U2 fully in VRAM at Q6_K (about 15 GB of 16 GB), at roughly 19 tokens/s.
- How fast does InternLumina-U2 run on the RTX A4000?
- An estimate from memory bandwidth gives about 19 tokens/s at Q6_K.
- Which quantisation of InternLumina-U2 should I use on the RTX A4000?
- Q6_K: 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.