Downloads · 30 days
21
20% of all-time downloads
amiko-hermit-1.0-27b-vl-mlx-4bit
mars2titan/amiko-hermit-1.0-27b-vl-mlx-4bit
amiko-hermit-1.0-27b-vl-mlx-4bit is a image-text-to-text model from mars2titan. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
27B vision-language model for tool use. Fine-tuned from Qwen3.8-27B on OpenHermit traces, then converted to 4-bit MLX for Apple Silicon. Vision encoder and MTP draft head are kept.
All-time downloads
106
Public
Parameters
27.4B
16.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
Parameter types
How the weights are stored.
U3226.9B · 98%
Try a prompt
Base models
Model card
From the Hugging Face model README
Amiko Hermit 1.0
27B vision-language model for tool use. Fine-tuned from Qwen3.8-27B on OpenHermit traces, then converted to 4-bit MLX for Apple Silicon. Vision encoder and MTP draft head are kept.
Eval
Held-out tool-call split, 260 calls, greedy decode, 256 new tokens. Compared to the untuned Qwen3.8-27B base.
| Base | Amiko Hermit 1.0 | |
|---|---|---|
| Valid JSON | 94/260 (36%) | 250/260 (96%) |
| Tool name exact | 56/260 (22%) | 156/260 (60%) |
Training
Loss 3.18 → 0.62, token accuracy 47% → 85% over 250 steps (1 epoch). Curves are on the TensorBoard tab.
Use with MLX
pip install -U mlx-vlm
python -m mlx_vlm.generate \
--model mars2titan/amiko-hermit-1.0-27b-vl-mlx-4bit \
--max-tokens 256 --temperature 0.0 \
--prompt "Describe this image." --image <path>
python -m mlx_vlm.server --model mars2titan/amiko-hermit-1.0-27b-vl-mlx-4bit
Use mlx-vlm, not mlx-lm, so vision stays.
Specs
- Architecture: Qwen3.5 vision-language (
Qwen3_5ForConditionalGeneration) - Quant: affine 4-bit, group size 64, 4.695 bits/weight, ~15 GB (3 shards)
- Train: 1 epoch, 250 steps, QLoRA r=16 α=32. Loss 3.18 → 0.62, token accuracy 47% → 85%
- License: Apache 2.0
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Languages
- en
- Created
- Aug 25, 2026
- Updated
- Aug 25, 2026