janhq / Jan-v2-VL-max-FP8

huggingface.co
Total runs: 107
24-hour runs: 0
7-day runs: 17
30-day runs: 87
Model's Last Updated: December 22 2025
image-text-to-text

Introduction of Jan-v2-VL-max-FP8

Model Details of Jan-v2-VL-max-FP8

Jan-v2-VL: Multimodal Agent for Long-Horizon Tasks

GitHub License Jan App

image

Overview

Jan-v2-VL-max extends the Jan-v2-VL family to a 30B-parameter vision–language model focused on long-horizon execution . This release scales model capacity and applies LoRA-based RLVR to improve stability over many steps with low error accumulation . For evaluation, we continue to use The Illusion of Diminishing Returns: Measuring Long-Horizon Execution in LLMs , which emphasizes execution length rather than knowledge recall.

Intended Use

Tasks where the plan and/or knowledge can be provided up front, and success hinges on stable, many-step execution with minimal drift:

  • Agentic automation & UI control: Stepwise operation in browsers/desktop apps with screenshot grounding and tool calls via Jan Browser MCP .
Model Performance

Evaluated under FP8 inference, Jan-v2-VL-max vs. Qwen3-VL-30B-A3B-Thinking shows no regressions and small gains on several tasks, with the largest improvements in long-horizon execution . Our FP8 build maintains accuracy while reducing memory footprint and latency.

image

Local Deployment
Jan Web

Hosted on Jan Web — use the model directly at chat.jan.ai

image/gif

Local Deployment

Using vLLM: We recommend vLLM for serving and inference. All reported results were run with vLLM 0.12.0 . For FP8 deployment, we used llm-compressor built from source. Please pin transformers==4.57.1 for compatibility.

# Exact versions used in our evals
pip install vllm==0.12.0
pip install transformers==4.57.1
pip install "git+https://github.com/vllm-project/llm-compressor.git@1abfd9eb34a2941e82f47cbd595f1aab90280c80"
vllm serve Menlo/Jan-v2-VL-max-FP8 \
    --host 0.0.0.0 \
    --port 1234 \
    -dp 1 \
    --enable-auto-tool-choice \
    --tool-call-parser hermes \
    --reasoning-parser deepseek_r1 
    
Recommended Parameters

For optimal performance in agentic and general tasks, we recommend the following inference parameters:

temperature: 1.0
top_p: 0.95
top_k: 20
repetition_penalty: 1.0
presence_penalty: 1.5
🤝 Community & Support
📄 Citation
Updated Soon

Runs of janhq Jan-v2-VL-max-FP8 on huggingface.co

107
Total runs
0
24-hour runs
6
3-day runs
17
7-day runs
87
30-day runs

More Information About Jan-v2-VL-max-FP8 huggingface.co Model

More Jan-v2-VL-max-FP8 license Visit here:

https://choosealicense.com/licenses/apache-2.0

Jan-v2-VL-max-FP8 huggingface.co

Jan-v2-VL-max-FP8 huggingface.co is an AI model on huggingface.co that provides Jan-v2-VL-max-FP8's model effect (), which can be used instantly with this janhq Jan-v2-VL-max-FP8 model. huggingface.co supports a free trial of the Jan-v2-VL-max-FP8 model, and also provides paid use of the Jan-v2-VL-max-FP8. Support call Jan-v2-VL-max-FP8 model through api, including Node.js, Python, http.

Jan-v2-VL-max-FP8 huggingface.co Url

https://huggingface.co/janhq/Jan-v2-VL-max-FP8

janhq Jan-v2-VL-max-FP8 online free

Jan-v2-VL-max-FP8 huggingface.co is an online trial and call api platform, which integrates Jan-v2-VL-max-FP8's modeling effects, including api services, and provides a free online trial of Jan-v2-VL-max-FP8, you can try Jan-v2-VL-max-FP8 online for free by clicking the link below.

janhq Jan-v2-VL-max-FP8 online free url in huggingface.co:

https://huggingface.co/janhq/Jan-v2-VL-max-FP8

Jan-v2-VL-max-FP8 install

Jan-v2-VL-max-FP8 is an open source model from GitHub that offers a free installation service, and any user can find Jan-v2-VL-max-FP8 on GitHub to install. At the same time, huggingface.co provides the effect of Jan-v2-VL-max-FP8 install, users can directly use Jan-v2-VL-max-FP8 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Jan-v2-VL-max-FP8 install url in huggingface.co:

https://huggingface.co/janhq/Jan-v2-VL-max-FP8

Url of Jan-v2-VL-max-FP8

Jan-v2-VL-max-FP8 huggingface.co Url

Provider of Jan-v2-VL-max-FP8 huggingface.co

janhq
ORGANIZATIONS

Other API from janhq

huggingface.co

Total runs: 3.3K
Run Growth: -475
Growth Rate: -14.49%
Updated:August 13 2025
huggingface.co

Total runs: 1.2K
Run Growth: 845
Growth Rate: 69.38%
Updated:March 24 2026
huggingface.co

Total runs: 1.1K
Run Growth: 118
Growth Rate: 11.17%
Updated:March 04 2026
huggingface.co

Total runs: 429
Run Growth: -159
Growth Rate: -37.06%
Updated:August 23 2025
huggingface.co

Total runs: 57
Run Growth: 13
Growth Rate: 22.81%
Updated:November 14 2025
huggingface.co

Total runs: 49
Run Growth: -66
Growth Rate: -134.69%
Updated:December 15 2023
huggingface.co

Total runs: 47
Run Growth: 19
Growth Rate: 40.43%
Updated:September 04 2025
huggingface.co

Total runs: 46
Run Growth: 14
Growth Rate: 30.43%
Updated:September 09 2025
huggingface.co

Total runs: 32
Run Growth: 4
Growth Rate: 12.50%
Updated:November 14 2025
huggingface.co

Total runs: 30
Run Growth: 11
Growth Rate: 36.67%
Updated:December 16 2025
huggingface.co

Total runs: 5
Run Growth: -4
Growth Rate: -80.00%
Updated:May 23 2024
huggingface.co

Total runs: 3
Run Growth: -3
Growth Rate: -100.00%
Updated:May 24 2024
huggingface.co

Total runs: 1
Run Growth: -2
Growth Rate: -200.00%
Updated:December 21 2023