unslothai/unsloth

[Feature] Draft model / speculative decoding

Closed

#4,753 opened on Apr 1, 2026

View on GitHubContributor guide
 (4 comments) (2 reactions) (0 assignees)Python (5,658 forks)batch import
feature requestgood first issuehelp wanted

Repository metrics

Stars
 (64,271 stars)
PR merge metrics
 (Avg merge 3d 15h) (525 merged PRs in 30d)

Description

Can we have the possibility to select draft model in ui? Seems like an important feature, I wonder how fast would Qwen3.5 27b be if I used Qwen3.5 0.8b as draft model.

Contributor guide

Research direction
Explore the existing speculative decoding implementation in the backend and add a UI toggle to select a draft model.
Tech stack
python
Domain
frontend
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonUI
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50