What are the hardware requirements for Qwen3.8 27B FP8?

Qwen3.8 27B FP8 requires approximately 29.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.8 27B FP8 and how large is it?

Qwen3.8 27B FP8 is developed by VIDraft, 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 27B FP8?

Qwen3.8 27B FP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.8 27B FP8 by VIDraft — VRAM 29.9GB

Name: Qwen3.8 27B FP8
Author: VIDraft

Qwen3.8 27B FP8 is an open-source language model by VIDraft. Features: 27b LLM, VRAM: 29.9GB, License: apache-2.0, LLM Explorer Score: 0.34.

Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-27b Compressed-tensors Conversational En Fp8 Ja Ko Long-context Quantized Qwen3 5 Reasoning Region:us Safetensors Sharded Tensorflow Vidraft Vllm Zh

Model Card on HF 🤗: https://huggingface.co/VIDraft/Qwen3.8-27B-FP8

Qwen3.8 27B FP8 Parameters and Internals

LLM Name	Qwen3.8 27B FP8
Repository 🤗	https://huggingface.co/VIDraft/Qwen3.8-27B-FP8
Base Model(s)	Qwen/Qwen3.8-27B Qwen/Qwen3.8-27B
Model Size	27b
Required VRAM	29.9 GB
Updated	2026-08-27
Maintainer	VIDraft
Model Type	qwen3_5
Model Files	4.0 GB: 1-of-8 4.0 GB: 2-of-8 3.9 GB: 3-of-8 4.0 GB: 4-of-8 4.0 GB: 5-of-8 3.9 GB: 6-of-8 3.6 GB: 7-of-8 2.5 GB: 8-of-8
Supported Languages	en ko zh ja
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.14.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.8 27B FP8 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 Qwen3.8 27B FP8

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.8 27B MLX	0K / 16 GB	1411	18
Qwen3.8 27B	0K / 55.6 GB	2727	21
Qwen3.8 27B FP8	0K / 0.4 GB	123157	416
Qwen3.6 27B	0K / 55.4 GB	6728138	2197
Qwen3.8 27B	0K / 55.6 GB	2	8753
Qwen3.6 27B NVFP4	0K / 22 GB	1887525	419
Qwen3.6 27B FP8	0K / 0.4 GB	7740472	342
ThinkingCap Qwen3.6 27B	0K / 54.7 GB	35947	614
Qwen3.5 27B	0K / 55.2 GB	2536294	1028
Qwen3.5 27B	0K / 55.2 GB	8115	16

Note: green Score (e.g. "73.2") means that the model is better than VIDraft/Qwen3.8-27B-FP8.