Jan-v2-VL-max needs about 19.9 GB of memory at Q4_K_M (a 18.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 15 quants, from 13.3 GB (Q3_K_S) to 61.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Jan‑v2‑VL‑max: 30B‑parameter vision‑language model for long‑horizon agentic tasks
Jan‑v2‑VL‑max extends the Jan‑v2‑VL family to a 30.5‑billion‑parameter vision‑language model. It focuses on stable, many‑step execution with low error accumulation. The model supports reasoning and vision tasks with a 262144‑token context.
Good at
- Long‑horizon agentic execution
- Vision‑language reasoning
- Stable multi‑step planning
Limits
- No vision support on older quantizations
- Large memory requirement for high‑quality quant
- Requires FP8 for optimal performance
Best for
- Browser automation with screenshot grounding
- Desktop UI control via tool calls
- Complex multi‑step visual tasks
Who it’s for. Developers building autonomous agents that need to interact with visual interfaces over many steps. Researchers testing long‑horizon reasoning in vision‑language models.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 13.3 GB | 14.6 GB | Too big | Get file → | |
| Q3_K_M | 14.7 GB | 16.0 GB | Too big | Get file → | |
| Q3_K_L | 15.9 GB | 17.2 GB | Too big | Get file → | |
| Q4_0 | 17.3 GB | 18.6 GB | Too big | Get file → | |
| Q4_K_S | 17.5 GB | 18.8 GB | Too big | Get file → | |
| Q4_K_M | 18.6 GB | 19.9 GB | Too big | Get file → | |
| Q4_1 | 19.2 GB | 20.5 GB | Too big | Get file → | |
| Q4_K_XL | 21.0 GB | 22.3 GB | Too big | Get file → | |
| Q5_0 | 21.1 GB | 22.4 GB | Too big | Get file → | |
| Q5_K_S | 21.1 GB | 22.4 GB | Too big | Get file → | |
| Q5_K_M | 21.7 GB | 23.0 GB | Too big | Get file → | |
| Q5_1 | 23.0 GB | 24.3 GB | Too big | Get file → | |
| Q6_K | 25.1 GB | 26.4 GB | Too big | Get file → | |
| Q8_0 | 32.5 GB | 33.8 GB | Too big | Get file → | |
| — | 61.1 GB | 62.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_S (13.29 GB file, ~14.6 GB memory). For 12 GB VRAM, Q4_0 (17.3 GB file, ~18.6 GB memory) is suitable. For 16 GB VRAM, Q5_K_M (21.73 GB file, ~23 GB memory) provides higher quality with acceptable memory usage. Estimates are approximate.
What GPU do you need for Jan-v2-VL-max?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q3_K_M (14.7 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (21.7 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (25.1 GB file, about 26.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (32.5 GB file, about 33.8 GB in use).
Which Jan-v2-VL-max quant should you choose?
Q4_K_M is the usual starting point for Jan-v2-VL-max: it balances file size and quality well. Here it is a 18.6 GB file.
The Q8_0 file is 32.5 GB, about 1.8 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 Q3_K_S at 13.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Jan-v2-VL-max
How much VRAM does Jan-v2-VL-max need?
About 19.9 GB at Q4_K_M with an 8K context window. That is the 18.6 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-max on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Jan-v2-VL-max GGUF?
It depends on the quant: Q3_K_S is 13.3 GB, Q3_K_M is 14.7 GB, Q3_K_L is 15.9 GB, Q4_0 is 17.3 GB, Q4_K_S is 17.5 GB, Q4_K_M is 18.6 GB and 9 more.
What context length does Jan-v2-VL-max support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.
Where can I download Jan-v2-VL-max GGUF?
The files are on Hugging Face in the janhq/Jan-v2-VL-max-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-max 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‑max on 8 GB VRAM?
Use the Q3_K_S quantization; it requires about 14.6 GB memory at 8k context, which exceeds 8 GB VRAM, so it is not feasible without further optimization.
Does the model support vision tasks?
Yes, it includes vision capabilities and is designed for vision‑language reasoning.
What license applies to this model?
The model is released under the apache‑2.0 license.