What are the hardware requirements for Qwen3.8 3.6 27B Blend?

Qwen3.8 3.6 27B Blend requires approximately 55.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.8 3.6 27B Blend and how large is it?

Qwen3.8 3.6 27B Blend is developed by JetBrains, a model with 27b 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 Qwen3.8 3.6 27B Blend?

Qwen3.8 3.6 27B Blend is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.8 3.6 27B Blend by JetBrains — VRAM 55.6GB

Name: Qwen3.8 3.6 27B Blend
Author: JetBrains

Qwen3.8 3.6 27B Blend is an open-source language model by JetBrains. Features: 27b LLM, VRAM: 55.6GB, License: apache-2.0, LLM Explorer Score: 0.25.

Base model:merge:qwen/qwen3.6-... Base model:merge:qwen/qwen3.8-... Base model:qwen/qwen3.6-27b Base model:qwen/qwen3.8-27b Conversational Endpoints compatible Image-text-to-text Linear-merge Merge Qwen3 5 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/JetBrains/Qwen3.8-3.6-27B-blend

Qwen3.8 3.6 27B Blend Parameters and Internals

LLM Name	Qwen3.8 3.6 27B Blend
Repository 🤗	https://huggingface.co/JetBrains/Qwen3.8-3.6-27B-blend
Base Model(s)	Qwen/Qwen3.6-27B Qwen/Qwen3.8-27B Qwen/Qwen3.6-27B Qwen/Qwen3.8-27B
Model Size	27b
Required VRAM	55.6 GB
Updated	2026-09-20
Maintainer	JetBrains
Model Type	qwen3_5
Model Files	4.0 GB: 1-of-18 3.0 GB: 2-of-18 2.5 GB: 3-of-18 4.0 GB: 4-of-18 2.1 GB: 5-of-18 4.0 GB: 6-of-18 2.1 GB: 7-of-18 4.0 GB: 8-of-18 2.1 GB: 9-of-18 4.0 GB: 10-of-18 2.1 GB: 11-of-18 4.0 GB: 12-of-18 2.1 GB: 13-of-18 4.0 GB: 14-of-18 2.1 GB: 15-of-18 4.0 GB: 16-of-18 2.1 GB: 17-of-18 3.4 GB: 18-of-18
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.8.0.dev0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.8 3.6 27B Blend 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

Quantized Models of the Qwen3.8 3.6 27B Blend

Model	Likes	Downloads	VRAM
Qwen3.8 3.6 27B Blend MLX 4bit	2	190	16 GB

Best Alternatives to Qwen3.8 3.6 27B Blend

Best Alternatives	Context / RAM	Downloads	Likes
...wopus3.8 27B Flash Mlx OQ4e 1M	1024K / 16.9 GB	211	1
Agens Pilot	1024K / 54.7 GB	86	3
... 27B 6.3bpw RCO SAR Marlin MTP	256K / 22 GB	84	1
Qwen3.8 27B NPU2	256K / GB	252	4
...toTrust Decider Pro Vision 27B	0K / 55.6 GB	1537390	4526
JEV 27B VL	0K / 55.6 GB	1525286	966
Clef	0K / 54.7 GB	22043	2237
Arete 27B	0K / 54.7 GB	2407	346
Qwen3.6 27B	0K / 55.4 GB	6728138	2197
Qwen3.8 27B	0K / 55.6 GB	2	8753

Note: green Score (e.g. "73.2") means that the model is better than JetBrains/Qwen3.8-3.6-27B-blend.