What are the hardware requirements for Qwen3.8 27B DFlash2 FP8?

Qwen3.8 27B DFlash2 FP8 requires approximately 2.1 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 Qwen3.8 27B DFlash2 FP8 and how large is it?

Qwen3.8 27B DFlash2 FP8 is developed by kusuriya-labs, 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 DFlash2 FP8?

Qwen3.8 27B DFlash2 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 DFlash2 FP8 by kusuriya-labs — VRAM 2.1GB, 256K context

Name: Qwen3.8 27B DFlash2 FP8
Author: kusuriya-labs

Qwen3.8 27B DFlash2 FP8 is an open-source language model by kusuriya-labs. Features: 27b LLM, VRAM: 2.1GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.29.

Base model:quantized:z-lab/qwe... Base model:z-lab/qwen3.8-27b-d... Dflash2 Draft-model Fp8 Quantized Qwen3 Region:us Rocm Safetensors Speculative-decoding

Model Card on HF 🤗: https://huggingface.co/kusuriya-labs/Qwen3.8-27B-DFlash2-FP8

Qwen3.8 27B DFlash2 FP8 Parameters and Internals

LLM Name	Qwen3.8 27B DFlash2 FP8
Repository 🤗	https://huggingface.co/kusuriya-labs/Qwen3.8-27B-DFlash2-FP8
Base Model(s)	z-lab/Qwen3.8-27B-DFlash2 z-lab/Qwen3.8-27B-DFlash2
Model Size	27b
Required VRAM	2.1 GB
Updated	2026-11-10
Maintainer	kusuriya-labs
Model Type	qwen3
Model Files	2.1 GB
Model Architecture	DFlash2DraftModel
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	5.15.0
Vocabulary Size	248320

Rank the Qwen3.8 27B DFlash2 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 DFlash2 FP8

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.8 27B DFlash2	256K / 3.9 GB	17062	124
Qwen3.8 27B DFlash2	256K / 3.9 GB	12235	148
Qwen3.8 27B DFlash2 Memra	256K / 3.9 GB	831	1
...wen3.8 27B DFlash2 EXL3 5.0bpw	256K / 1.5 GB	605	7
...en3.8 27B DFlash2 EXL3 4.00bpw	256K / 1.2 GB	388	2
...en3.8 27B DFlash2 EXL3 4.00bpw	256K / 1.2 GB	163	1
Qwen3.8 27B DFlash2 Memra	256K / 3.9 GB	329	2
...wen3.8 27B Heretic Ara DFlash2	256K / 3.9 GB	371	1
...en3.6 27B Nothink DFlash2 V0.1	256K / 3.9 GB	107	0
Qwen3.8 27B Test DFlash2 V0.3	256K / 3.9 GB	38	0

Note: green Score (e.g. "73.2") means that the model is better than kusuriya-labs/Qwen3.8-27B-DFlash2-FP8.