Downloads · 30 days
164
33% of all-time downloads
Qwen3-8B-speculator.dspark
mgoin/Qwen3-8B-speculator.dspark
Qwen3-8B-speculator.dspark 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.
DSpark (DFlash backbone + Markov logit-bias head + confidence head) draft model for Qwen/Qwen3-8B, trained with speculators (PR 677).
All-time downloads
493
Public
Parameters
1.8B
3.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.7 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 DSpark speculator
DSpark (DFlash backbone + Markov logit-bias head + confidence head) 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): 0.689 / 0.541 / 0.440 / 0.369 / 0.319 / 0.283 / 0.255 | full_acc 0.415.
- Task
- Text Generation
- Library
- speculators
- Created
- Jun 28, 2026
- Updated
- Jun 28, 2026