WeMM Video 35BA3B
- In Input modalities: TextImage
- Tool use
- Open weights
Prices
0 offerings · prices as listedNo priced offering is listed for this model yet.
Details
- Licence
- apache-2.0
- Family
- wemm-video
Run locally
Weights: tencent/WeMM-Video-35BA3B- Parameters 36.2B
- Active 5B (estimated) · 256 experts, 8 per token
- Native precision BF16
- Layers 40
- KV cache per token 20 KB
- Config positions 256K (config.json max_position_embeddings)
- Needs
- ≈ 19.0 GB (weights 17.9 + KV cache 0.2 + overhead 0.9)
- Usable
- 21.6 GB (90% of its memory)
- Generation speed
- 179–269 tok/s (reads the active 5B per token)
- Longest context
- 143K (longer doesn’t fit)
- First token
- about 0.16–0.24 s for a 2K prompt
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native) | 67.4 GB | ≈ 70.9 | ○Needs system memory 6–9 tok/s | — |
| Q8_0 | 35.8 GB | ≈ 37.7 | ○Needs system memory 31–47 tok/s | — |
| FP8 | 33.7 GB | ≈ 35.5 | ○Needs system memory 33–49 tok/s | — |
| Q6_K | 27.7 GB | ≈ 29.2 | ○Needs system memory 40–60 tok/s | — |
| Q5_K_M | 24.0 GB | ≈ 25.3 | ○Needs system memory 51–77 tok/s | — |
| Q5_0 | 23.2 GB | ≈ 24.5 | ○Needs system memory 65–97 tok/s | — |
| Q4_K_M | 20.5 GB | ≈ 21.6 | ○Needs system memory 133–199 tok/s | — |
| Q4_0 | 19.0 GB | ≈ 20.1 | ●Runs well 170–255 tok/s | 87K |
| IQ4_XS | 17.9 GB | ≈ 19.0 | ●Runs well 179–269 tok/s | 143K |
| Q3_K_Mquality drops | 16.5 GB | ≈ 17.4 | ●Runs well 194–291 tok/s | 220K |
| IQ3_XXSquality drops | 12.9 GB | ≈ 13.7 | ●Runs well 244–365 tok/s | 256K |
| Q2_Kquality drops | 12.6 GB | ≈ 13.4 | ●Runs well 248–372 tok/s | 256K |
| IQ2_XXSquality drops | 8.7 GB | ≈ 9.3 | ●Runs well 348–522 tok/s | 256K |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): GPU GeForce RTX 5090; unified memory Apple M5 Max (32-core GPU) · 36 GB.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-21. How it’s estimated
Cited scores
From third-party leaderboards, not measured by usThis model isn’t on any leaderboard we cite yet.
Changes
All changes →- New language model
Sources
- tencent/WeMM-Video-35BA3B model card (opens in a new tab) huggingface.co · checked Nov 20, 2026
- tencent/WeMM-Video-35BA3B config.json (opens in a new tab) huggingface.co · checked Nov 20, 2026
- tencent/WeMM-Video-35BA3B model card (opens in a new tab) huggingface.co · checked Nov 20, 2026
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Tencent · China · tencent.com
Related models
Snapshots, the same family and other models from this provider