LLM EXPLORER 56,604 MODELS INDEXED

Jan V1.2509 by janhq

By janhq · 15 downloads
HF Repo ↗ Copy URL

Jan V1.2509 is an open-source language model by janhq. Features: 4b LLM, VRAM: 8.1GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.2.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-4b-think...   Conversational   Deploy:azure   En   Endpoints compatible   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/janhq/Jan-v1-2509 

Jan V1.2509 Parameters and Internals

LLM NameJan V1.2509
Repository 🤗https://huggingface.co/janhq/Jan-v1-2509 
Base Model(s)  Qwen3 4B Thinking 2507   Qwen/Qwen3-4B-Thinking-2507
Model Size4b
Required VRAM8.1 GB
Updated2026-07-27
Maintainerjanhq
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.1 GB: 2-of-2   0.0 GB
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.55.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Jan V1.2509

Best Alternatives
Context / RAM
Downloads
Likes
Fable Traces256K / 8.1 GB5530209
FastContext 1.0 4B SFT256K / 8.1 GB5735357
Qwen3 4B Instruct 2507256K / 8.1 GB3109972911
GRPO 4 70256K / 8.1 GB60
Lightning 4B256K / 8.1 GB136
FastContext 1.0 4B RL256K / 8.1 GB455961
Qwen3 4B Thinking 2507256K / 8.1 GB291023606
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB110074478
Typhoon2.5 Qwen3 4B256K / 8 GB4898776
Neuron 4B Instruct256K / 8.1 GB3131
Note: green Score (e.g. "73.2") means that the model is better than janhq/Jan-v1-2509.