Can the Tesla T4 run WeMM-Video-9B?
WeMM-Video-9B·10.5B·Tesla T4·16 GB VRAM
Saved in this browser, used on every model page.
Yes
Yes. The Tesla T4 runs WeMM-Video-9B fully in VRAM at Q8_0 (about 12 GB of 16 GB), at roughly 16 tokens/s.
- best quant
- Q8_0
- needs
- 12 GB
- usable
- 16 GB
- est. speed
- ~16 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the WeMM-Video-9B page →
Every quantisation of WeMM-Video-9B on the Tesla T4
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 4.9 GB | fits | ~51 tok/s |
| Q3_K_M | 6.5 GB | fits | ~34 tok/s |
| Q4_K_M | 7.7 GB | fits | ~28 tok/s |
| Q5_K_M | 8.8 GB | fits | ~24 tok/s |
| Q6_K | 9.9 GB | fits | ~20 tok/s |
| Q8_0 pick | 12 GB | fits | ~16 tok/s |
| FP16 / BF16 | 22 GB | offload | ~3.8 tok/s |
Speed is a bandwidth-based estimate for generating text (320 GB/s); prompt processing and long contexts are slower.
Measured speed on the Tesla T4
No community reports for this pair yet.
Report your own speed →Vision models that fit the Tesla T4 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 9.7B | Q8_0 | ≈11 GBFits in memory | ~17 tok/s | |
| 8.8B | Q8_0 | ≈10 GBFits in memory | ~19 tok/s | |
| 12.2B | Q6_K | ≈13 GBFits in memory | ~18 tok/s | |
| 10.7B | Q8_0 | ≈12 GBFits in memory | ~16 tok/s | |
| 9.4B | Q8_0 | ≈11 GBFits in memory | ~18 tok/s | |
| 8.3B | Q8_0 | ≈8.9 GBFits in memory | ~20 tok/s |
Other GPUs that run WeMM-Video-9B
Frequently asked questions
- Can the Tesla T4 run WeMM-Video-9B?
- Yes. The Tesla T4 runs WeMM-Video-9B fully in VRAM at Q8_0 (about 12 GB of 16 GB), at roughly 16 tokens/s.
- How fast does WeMM-Video-9B run on the Tesla T4?
- An estimate from memory bandwidth gives about 16 tokens/s at Q8_0.
- Which quantisation of WeMM-Video-9B should I use on the Tesla T4?
- 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.