Downloads · 30 days
60
40% of all-time downloads
Qwen3-8B-speculator.dflash
mgoin/Qwen3-8B-speculator.dflash
Qwen3-8B-speculator.dflash is a text generation model from mgoin. Use it when you need the model to write or continue text. It is set up for speculators.
DFlash draft model, trained identically to the DSpark checkpoint as an A/B baseline, draft model for Qwen/Qwen3-8B, trained with speculators (PR 677).
All-time downloads
151
Public
Parameters
1.8B
3.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.6 GB · 100%
Parameter types
How the weights are stored.
BF161.8B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-8B DFlash speculator (matched baseline)
DFlash draft model, trained identically to the DSpark checkpoint as an A/B baseline, draft model for Qwen/Qwen3-8B, trained with
speculators (PR #677).
Preview/research checkpoint: online training on a 20k ShareGPT slice, seq 2048, 3 epochs.
Validation per-position acceptance (pos1-7): 0.665 / 0.474 / 0.338 / 0.243 / 0.180 / 0.141 / 0.115 | full_acc 0.309.
- Task
- Text Generation
- Library
- speculators
- Created
- Jun 28, 2026
- Updated
- Jun 28, 2026