Downloads · 30 days
10
18% of all-time downloads
hzplan-edit-17-f09-q8
madmag77/hzplan-edit-17-f09-q8
hzplan-edit-17-f09-q8 is a machine learning model from madmag77. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx.
Qwen3-1.7B fine-tuned for HZPlan voice floor-plan editing (MCP tool calls), F0.9 rebalance recipe (same f09-dataset as the 0.6B). Fused from W&B f09-17-adapter, mlx q8.
All-time downloads
57
Public
Parameters
1.7B
1.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.8 GB · 99%
Parameter types
How the weights are stored.
U321.7B · 100%
Base models
Model card
From the Hugging Face model README
hzplan-edit-17-f09-q8
Qwen3-1.7B fine-tuned for HZPlan voice floor-plan editing (MCP tool calls),
F0.9 rebalance recipe (same f09-dataset as the 0.6B). Fused from W&B
f09-17-adapter, mlx q8.
Edit specialist with a QA trade-off (F0.8-era held-out packs, same scorer as all baselines):
| pack | 0.6B f09 | 1.7B f09 |
|---|---|---|
| eval_v2e (60) | 85% | 87% (best of any model on this pack) |
| 25-pack | 76% | 84% (T3 compositions 9/11 vs 7/11) |
| qa_v3 (45) | 60% | 36% — obj_size 0/9, gap 0/10; audited: real misses |
Use for edit-heavy sessions (relative placements, compositions) at ~2× 0.6B
latency; prefer the 0.6B (hzplan-edit-06-f09-q8) or 4B for QA-heavy use.
The QA collapse at 1.7B (not seen at 0.6B on identical data) is an open
investigation — see experiments/2026-07-10-h6-f09-rebalance.
- Library
- mlx
- Type
- qwen3
- Created
- Jul 11, 2026
- Updated
- Jul 11, 2026