Can the Radeon RX 7900 XTX run NLD-Uni?
NLD-Uni·18.3B·Radeon RX 7900 XTX·24 GB VRAM
Saved in this browser, used on every model page.
Yes
Yes. The Radeon RX 7900 XTX 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 Radeon RX 7900 XTX
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 7.4 GB | fits | ~88 tok/s |
| Q3_K_M | 10 GB | fits | ~59 tok/s |
| Q4_K_M | 12 GB | fits | ~48 tok/s |
| Q5_K_M | 14 GB | fits | ~41 tok/s |
| Q6_K | 16 GB | fits | ~35 tok/s |
| Q8_0 pick | 21 GB | fits | ~27 tok/s |
| FP16 / BF16 | 37 GB | offload | ~2.3 tok/s |
Speed is a bandwidth-based estimate for generating text (960 GB/s); prompt processing and long contexts are slower.
Measured speed on the Radeon RX 7900 XTX
No community reports for this pair yet.
Report your own speed →Omni models that fit the Radeon RX 7900 XTX comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 17.5B | Q8_0 | ≈20 GBFits in memory | ~28 tok/s | |
| 12B | Q8_0 | ≈16 GBFits in memory | ~42 tok/s | |
| 24.3B | Q6_K | ≈21 GBFits in memory | ~26 tok/s | |
| 14.7B | Q8_0 | ≈17 GBFits in memory | ~34 tok/s | |
| 10.7B | Q8_0 | ≈8.9 GBFits in memory | ~46 tok/s | |
| 35.3BA3B | Q4_K_M | ≈19 GBFits in memory | ~290 tok/s |
Other GPUs that run NLD-Uni
Frequently asked questions
- Can the Radeon RX 7900 XTX run NLD-Uni?
- Yes. The Radeon RX 7900 XTX 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 Radeon RX 7900 XTX?
- An estimate from memory bandwidth gives about 27 tokens/s at Q8_0.
- Which quantisation of NLD-Uni should I use on the Radeon RX 7900 XTX?
- 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.