WeVisOne VL 2B
WeVisOne VL 2B is an open-weights language model from Tencent, released October 22, 2026. It has 2.4B parameters (dense). The context window is 256K tokens.
Check it against your own PC →
Can you run WeVisOne VL 2B locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, fully on GPU, roughly 54 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 | Q6_K (≈ lossless) | 4.5 GB | – | ~54 |
| 8 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.5 GB | – | ~75 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.5 GB | – | ~97 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.5 GB | – | ~130 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.5 GB | – | ~220 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.5 GB | – | ~350 |
Ready-made quantizations on Hugging Face: mradermacher/WeVisOne-VL-2B-GGUF · PALLER-NOVUS/WeVisOne-VL-GGUF · prithivMLmods/tencent-WeVisOne-VL-2B-GGUF · litert-community/WeVisOne-VL-2B · t8star/WeVisOne-VL-Comfy · mlboydaisuke/WeVisOne-VL-2B-CoreAI
Benchmark results
Epoch AI has not published results for WeVisOne VL 2B yet. New models are usually evaluated within days to weeks.
Links
Hugging Face: tencent/WeVisOne-VL-2B
More from Tencent
WeVisOne VL 4B · Hy Memory 30B A3B · Youtu Parsing Omni · Tencent Hy4 preview · Hy4 preview · Tencent Hy3