Youtu Parsing Omni
Youtu Parsing Omni is an open-weights language model from Tencent, released October 9, 2026. It has 5.3B parameters (dense). The context window is 1M tokens.
Check it against your own PC →
Can you run Youtu Parsing Omni locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q5_K_M, fully on GPU, roughly 29 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Runs on GPU | Q5_K_M (excellent) | 5.1 GB | – | ~29 |
| 8 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 5.7 GB | – | ~36 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 5.7 GB | – | ~47 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 5.7 GB | – | ~64 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 5.7 GB | – | ~110 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 5.7 GB | – | ~200 |
Ready-made quantizations on Hugging Face: cguldogan/Youtu-Parsing-Omni-mlx-8bit · cguldogan/Youtu-Parsing-Omni-mlx-4bit
Benchmark results
Epoch AI has not published results for Youtu Parsing Omni yet. New models are usually evaluated within days to weeks.
Links
Hugging Face: tencent/Youtu-Parsing-Omni
More from Tencent
WeVisOne VL 4B · WeVisOne VL 2B · Hy Memory 30B A3B · Tencent Hy4 preview · Hy4 preview · Tencent Hy3