Downloads · 30 days
6
16% of all-time downloads
hzplan-edit-06-f08-q8
madmag77/hzplan-edit-06-f08-q8
hzplan-edit-06-f08-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.
Qwen3-0.6B fine-tuned for HZPlan voice floor-plan editing (MCP tool calls), F0.8 recipe (compositions + declarative phrasing + robustness), fused LoRA (adapters-f08-06/final, W&B f08-lora-06), mlx q8 (8.5 bits/weight).
All-time downloads
38
Public
Parameters
596M
645 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors633 MB · 98%
Parameter types
How the weights are stored.
U32596M · 100%
Base models
Model card
From the Hugging Face model README
hzplan-edit-06-f08-q8
Qwen3-0.6B fine-tuned for HZPlan voice floor-plan editing (MCP tool calls),
F0.8 recipe (compositions + declarative phrasing + robustness), fused LoRA
(adapters-f08-06/final, W&B f08-lora-06), mlx q8 (8.5 bits/weight).
F0.8 0.6B eval (vs F0.7a): held-out new-kind compositions 5→11/20;
eval-v2e 70→67 (capacity seesaw — QA displaced). Best for testing the new
composition families (opening-relative, object-in-corner, declarative forms)
at 0.6B latency; the 4B F0.8 (madmag77/hzplan-edit-4b-f08-q8) remains the
quality reference.
Serve with ModelProbe (custom model id) or mlx_lm with the mini prompt.
Smoke-tested through the full agent loop: 3/3 pass, ~2.5 s/case (Mac q8).
- Library
- mlx
- Type
- qwen3
- Created
- Jul 10, 2026
- Updated
- Jul 10, 2026