Can the RTX 5090 run WeMM-Video-35BA3B?
WeMM-Video-35BA3B·36.2B (5B active)·GeForce RTX 5090·32 GB VRAM
Yes. The RTX 5090 runs WeMM-Video-35BA3B fully in VRAM at Q6_K (about 30 GB of 32 GB), at roughly 241 tokens/s.
- best quant
- Q6_K
- needs
- 30 GB
- usable
- 32 GB
- est. speed
- ~241 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the WeMM-Video-35BA3B page →
Every quantisation of WeMM-Video-35BA3B on the RTX 5090
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 13 GB | fits | ~603 tok/s |
| Q3_K_M | 18 GB | fits | ~406 tok/s |
| Q4_K_M | 23 GB | fits | ~327 tok/s |
| Q5_K_M | 26 GB | fits | ~279 tok/s |
| Q6_K pick | 30 GB | fits | ~241 tok/s |
| Q8_0 | 39 GB | offload | ~31 tok/s |
| FP16 / BF16 | 72 GB | too big | — |
Speed is a bandwidth-based estimate for generating text (1792 GB/s); prompt processing and long contexts are slower.
Measured speed on the RTX 5090
No community reports for this pair yet.
Report your own speed →Vision models that fit the RTX 5090 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 36BA3B | Q6_K | ≈30 GBFits in memory | ~399 tok/s | |
| 36BA3B | Q6_K | ≈29 GBFits in memory | ~399 tok/s | |
| 31.3B | Q5_K_M | ≈29 GBFits in memory | ~44 tok/s | |
| 27.8B | Q6_K | ≈25 GBFits in memory | ~43 tok/s | |
| 35.2BA3B | Q6_K | ≈29 GBFits in memory | ~399 tok/s | |
| 29.8B | Q8_0 | ≈30 GBFits in memory | ~31 tok/s |
Other GPUs that run WeMM-Video-35BA3B
Frequently asked questions
- Can the RTX 5090 run WeMM-Video-35BA3B?
- Yes. The RTX 5090 runs WeMM-Video-35BA3B fully in VRAM at Q6_K (about 30 GB of 32 GB), at roughly 241 tokens/s.
- How fast does WeMM-Video-35BA3B run on the RTX 5090?
- An estimate from memory bandwidth gives about 241 tokens/s at Q6_K.
- Which quantisation of WeMM-Video-35BA3B should I use on the RTX 5090?
- 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.