Jan-v2-VL-high needs about 7.2 GB of memory at Q4_K_M (a 5.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 27 quants, from 0.0 GB to 16.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Jan‑v2‑VL‑high: 8.2B‑parameter vision‑language model with 256K context
Jan‑v2‑VL‑high is an 8.2B‑parameter vision‑language model derived from Qwen3‑VL‑8B‑Thinking. It supports reasoning and vision tasks with a native context length of 262144 tokens. The model is released under the Apache‑2.0 license.
Good at
- Vision‑language reasoning
- Long‑context multimodal tasks
- Stable multi‑step execution
Limits
- No vision support on older quantizations
- Requires large VRAM for higher‑bit quant
- No explicit language list provided
Best for
- Complex GUI automation
- Multimodal document analysis
- Long‑horizon task planning
Who it’s for. Developers building multimodal agents that need extended context and robust visual reasoning. The model is suitable for applications requiring stable, multi‑step execution in software environments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.7 GB | Fits | Get file → | |
| IQ1_S | 2.5 GB | 4.2 GB | Fits | Get file → | |
| IQ1_M | 2.8 GB | 4.6 GB | Fits | Get file → | |
| IQ2_XXS | 2.9 GB | 4.6 GB | Fits | Get file → | |
| IQ2_XS | 3.1 GB | 4.8 GB | Fits | Get file → | |
| IQ2_S | 3.2 GB | 4.9 GB | Fits | Get file → | |
| Q2_K_S | 3.2 GB | 4.9 GB | Fits | Get file → | |
| IQ2_M | 3.3 GB | 5.0 GB | Fits | Get file → | |
| Q2_K_M | 3.4 GB | 5.1 GB | Fits | Get file → | |
| IQ3_XXS | 3.8 GB | 5.5 GB | Fits | Get file → | |
| IQ3_XS | 3.9 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_S | 4.2 GB | 5.9 GB | Fits | Get file → | |
| IQ3_M | 4.2 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_M | 4.3 GB | 6.0 GB | Fits | Get file → | |
| IQ4_NL | 4.6 GB | 6.3 GB | Fits | Get file → | |
| IQ4_XS | 4.7 GB | 6.4 GB | Fits | Get file → | |
| Q4_K_S | 5.0 GB | 6.7 GB | Fits | Get file → | |
| Q4_1 | 5.2 GB | 6.9 GB | Fits | Get file → | |
| Q4_0 | 5.2 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_M | 5.4 GB | 7.2 GB | Fits | Get file → | |
| Q5_0 | 6.1 GB | 7.8 GB | Tight | Get file → | |
| Q5_K_M | 6.3 GB | 8.0 GB | Tight | Get file → | |
| Q5_1 | 6.5 GB | 8.2 GB | Too big | Get file → | |
| Q6_K_M | 7.0 GB | 8.7 GB | Too big | Get file → | |
| Q8_0 | 8.7 GB | 10.4 GB | Too big | Get file → | |
| F16 | 12.3 GB | 14.0 GB | Too big | Get file → | |
| BF16 | 16.4 GB | 18.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (2.52 GB, 4.2 GB memory) or IQ1_M (2.84 GB, 4.6 GB memory). With 12 GB VRAM, Q4_K_M (5.45 GB, 7.2 GB memory) or Q5_0 (6.1 GB, 7.8 GB memory) provide a good balance of size and performance. Higher‑bit options such as Q8_0 (8.71 GB, 10.4 GB memory) require more memory but offer better precision.
What GPU do you need for Jan-v2-VL-high?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.7 GB in use).
- 6 GB VRAM: the best quant that fits is Q3_K_M (4.3 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (6.3 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
- 16 GB VRAM: the best quant that fits is F16 (12.3 GB file, about 14.0 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.4 GB file, about 18.1 GB in use).
Which Jan-v2-VL-high quant should you choose?
Q4_K_M is the usual starting point for Jan-v2-VL-high: it balances file size and quality well. Here it is a 5.4 GB file.
The Q8_0 file is 8.7 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Jan-v2-VL-high
How much VRAM does Jan-v2-VL-high need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Jan-v2-VL-high on an 8 GB GPU?
Yes, with Q5_K_M: the 6.3 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Jan-v2-VL-high GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 2.5 GB, IQ1_M is 2.8 GB, IQ2_XXS is 2.9 GB, IQ2_XS is 3.1 GB, IQ2_S is 3.2 GB and 21 more.
What context length does Jan-v2-VL-high support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Jan-v2-VL-high GGUF?
The files are on Hugging Face in the Mungert/Jan-v2-VL-high-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Jan-v2-VL-high use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Jan‑v2‑VL‑high on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quantizations which fit within 8 GB VRAM and use approximately 4.2–4.6 GB memory at 8K context.
Does the model support vision tasks?
Yes, the model has detected abilities for reasoning and vision, enabling multimodal input.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.