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

Qwen3.8 27B FP8 BLOCK requires approximately 36.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

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

Qwen3.8 27B FP8 BLOCK is developed by shisa-ai, 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 BLOCK?

Qwen3.8 27B FP8 BLOCK 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 BLOCK by shisa-ai — VRAM 36.2GB

Name: Qwen3.8 27B FP8 BLOCK
Author: shisa-ai

Qwen3.8 27B FP8 BLOCK is an open-source language model by shisa-ai. Features: 27b LLM, VRAM: 36.2GB, License: apache-2.0, LLM Explorer Score: 0.33.

Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-27b Compressed-tensors Conversational Endpoints compatible Fp8 Gdn Image-text-to-text Llm-compressor Quantized Qwen3.8 Qwen3 5 Region:us Safetensors Sharded Tensorflow

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

Qwen3.8 27B FP8 BLOCK Parameters and Internals

LLM Name	Qwen3.8 27B FP8 BLOCK
Repository 🤗	https://huggingface.co/shisa-ai/Qwen3.8-27B-FP8-BLOCK
Base Model(s)	Qwen/Qwen3.8-27B Qwen/Qwen3.8-27B
Model Size	27b
Required VRAM	36.2 GB
Updated	2026-08-19
Maintainer	shisa-ai
Model Type	qwen3_5
Model Files	2.8 GB: 1-of-18 1.9 GB: 2-of-18 2.5 GB: 3-of-18 2.5 GB: 4-of-18 1.3 GB: 5-of-18 2.5 GB: 6-of-18 1.2 GB: 7-of-18 2.5 GB: 8-of-18 1.2 GB: 9-of-18 2.5 GB: 10-of-18 1.2 GB: 11-of-18 2.5 GB: 12-of-18 1.2 GB: 13-of-18 2.5 GB: 14-of-18 1.2 GB: 15-of-18 2.5 GB: 16-of-18 1.2 GB: 17-of-18 3.0 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 27B FP8 BLOCK 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 BLOCK

Best Alternatives	Context / RAM	Downloads	Likes
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
ThinkingCap Qwen3.6 27B	0K / 54.7 GB	35947	614
Huihui Qwen3.8 27B Abliterated	0K / 55.6 GB	1485	76
Qwen3.6 27B FP8	0K / 0.4 GB	7740472	342
Qwen3.5 27B	0K / 55.2 GB	2536294	1028
...n3.8 27B MTPLX Optimized Speed	0K / 19.6 GB	6989	50
Qwen3.5 27B	0K / 55.2 GB	8115	16

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