LLM EXPLORER 63,529 MODELS INDEXED

Qwen3.8 27B Test DFlash2 V0.3 by vvsotnikov

By vvsotnikov · 38 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B Test DFlash2 V0.3 is an open-source language model by vvsotnikov. Features: 27b LLM, VRAM: 3.9GB, Context: 256K, LLM Explorer Score: 0.26.

  Qwen3   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/vvsotnikov/Qwen3.8-27B-test-DFlash2-v0.3 

Qwen3.8 27B Test DFlash2 V0.3 Parameters and Internals

LLM NameQwen3.8 27B Test DFlash2 V0.3
Repository 🤗https://huggingface.co/vvsotnikov/Qwen3.8-27B-test-DFlash2-v0.3 
Model Size27b
Required VRAM3.9 GB
Updated2026-10-01
Maintainervvsotnikov
Model Typeqwen3
Model Files  3.9 GB
Model ArchitectureDFlash2DraftModel
Context Length262144
Model Max Length262144
Transformers Version5.15.0
Vocabulary Size248320

Best Alternatives to Qwen3.8 27B Test DFlash2 V0.3

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.8 27B DFlash2256K / 3.9 GB17062124
Qwen3.8 27B DFlash2256K / 3.9 GB12235148
...en3.8 27B DFlash2 EXL3 4.00bpw256K / 1.2 GB3882
...wen3.8 27B DFlash2 EXL3 5.0bpw256K / 1.5 GB6057
Qwen3.8 27B DFlash2 Memra256K / 3.9 GB8311
...en3.6 27B Nothink DFlash2 V0.1256K / 3.9 GB1070
...en3.8 27B DFlash2 EXL3 4.00bpw256K / 1.2 GB1631
Qwen3.8 27B DFlash2 Memra256K / 3.9 GB5482
...wen3.8 27B Heretic Ara DFlash2256K / 3.9 GB3711
Qwen3.8 27B DFlash2 Exp0K / 3.9 GB1891
Note: green Score (e.g. "73.2") means that the model is better than vvsotnikov/Qwen3.8-27B-test-DFlash2-v0.3.