What are the hardware requirements for Jet?

Jet requires approximately 8.5 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Jet and how large is it?

Jet is developed by michaljach, a model with 4b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Jet?

Jet is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Jet by michaljach — VRAM 8.5GB, 256K context

Name: Jet
Author: michaljach

Jet is an open-source language model by michaljach. Features: 4b LLM, VRAM: 8.5GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.3.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-4b Conversational Decision-model En Endpoints compatible Qwen3 5 Qwen3 5 text Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/michaljach/jet

Jet Parameters and Internals

LLM Name	Jet
Repository 🤗	https://huggingface.co/michaljach/jet
Base Model(s)	Qwen/Qwen3.5-4B Qwen/Qwen3.5-4B
Model Size	4b
Required VRAM	8.5 GB
Updated	2026-09-26
Maintainer	michaljach
Model Type	qwen3_5_text
Model Files	1.3 GB: 1-of-9 1.0 GB: 2-of-9 1.0 GB: 3-of-9 1.0 GB: 4-of-9 1.0 GB: 5-of-9 1.0 GB: 6-of-9 1.0 GB: 7-of-9 1.0 GB: 8-of-9 0.2 GB: 9-of-9
Supported Languages	en
Model Architecture	Qwen3_5ForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	5.17.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	248320
Errors	replace

Rank the Jet capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Jet

Best Alternatives	Context / RAM	Downloads	Likes
Agents A1 4B Fable Preview	256K / 8.4 GB	103	0
NeoHorse 1 4B	256K / 8.4 GB	1771	179
Decider 4B	256K / 8.4 GB	23565	17
JevK5	256K / 8.4 GB	5525	13
JSBAI Coder 4B	256K / 8.4 GB	2795	1
Wald 4B	256K / 8.4 GB	706	7
Cisimcik 4B	256K / 8.4 GB	848	1
Aztec Coder 4B	256K / 8.4 GB	1197	4
WikiQwen 4B	256K / 8.4 GB	1125	2
Qwen 3.5 4B Auto ASVD	256K / 8.3 GB	988	1

Note: green Score (e.g. "73.2") means that the model is better than michaljach/jet.