What are the hardware requirements for Qwen3.8 Flash Next FP8?

Qwen3.8 Flash Next FP8 requires approximately 65.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.8 Flash Next FP8 and how large is it?

Qwen3.8 Flash Next FP8 is developed by unsloth, a model with 180b 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 Flash Next FP8?

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

Qwen3.8 Flash Next FP8 by unsloth — VRAM 65.7GB

Name: Qwen3.8 Flash Next FP8
Author: unsloth

Qwen3.8 Flash Next FP8 is an open-source language model by unsloth. Features: 180b LLM, VRAM: 65.7GB, License: other, LLM Explorer Score: 0.38.

Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-... Conversational Endpoints compatible Fp8 Image-text-to-text Qwen4 exp Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3.8-Flash-Next-FP8

Qwen3.8 Flash Next FP8 Parameters and Internals

LLM Name	Qwen3.8 Flash Next FP8
Repository 🤗	https://huggingface.co/unsloth/Qwen3.8-Flash-Next-FP8
Base Model(s)	Qwen/Qwen3.8-Flash-Next Qwen/Qwen3.8-Flash-Next
Model Size	180b
Required VRAM	65.7 GB
Updated	2026-08-28
Maintainer	unsloth
Model Type	qwen4_exp
Model Files	1.0 GB: 1-of-131 1.7 GB: 2-of-131 1.0 GB: 3-of-131 1.7 GB: 4-of-131 1.7 GB: 5-of-131 1.6 GB: 6-of-131 1.6 GB: 7-of-131 1.6 GB: 8-of-131 1.6 GB: 9-of-131 1.6 GB: 10-of-131 1.6 GB: 11-of-131 1.6 GB: 12-of-131 1.6 GB: 13-of-131 1.6 GB: 14-of-131 1.6 GB: 15-of-131 1.6 GB: 16-of-131 1.6 GB: 17-of-131 1.6 GB: 18-of-131 1.6 GB: 19-of-131 1.6 GB: 20-of-131 1.6 GB: 21-of-131 1.6 GB: 22-of-131 1.6 GB: 23-of-131 1.6 GB: 24-of-131 1.6 GB: 25-of-131 1.6 GB: 26-of-131 1.6 GB: 27-of-131 1.6 GB: 28-of-131 1.6 GB: 29-of-131 1.6 GB: 30-of-131 1.6 GB: 31-of-131 1.6 GB: 32-of-131 1.6 GB: 33-of-131 1.6 GB: 34-of-131 1.6 GB: 35-of-131 1.6 GB: 36-of-131 0.9 GB: 37-of-131 1.7 GB: 38-of-131 0.9 GB: 39-of-131 1.7 GB: 40-of-131 1.1 GB: 41-of-131 1.7 GB: 42-of-131 1.0 GB: 43-of-131
Model Architecture	Qwen4ExpForConditionalGeneration
License	other
Transformers Version	5.8.0.dev0

Rank the Qwen3.8 Flash Next 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 Flash Next FP8

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.8 Flash Next	0K / 129.5 GB	4810	3918
Qwen3.8 Flash Next FP8	0K / 65.7 GB	2219	117
Qwen3.8 Flash Next	0K / 129.5 GB	88	10
...en3.8 Flash Next DERISKED BF16	0K / 129.5 GB	0	1
Qwen3.8 Flash Next Abliterated	0K / 105.8 GB	0	1

Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3.8-Flash-Next-FP8.