Downloads · 30 days
19
6% of all-time downloads
TheCluster/Crow-9B-HERETIC-4.6-MLX-8bit
Crow-9B-HERETIC-4.6-MLX-8bit is a image-text-to-text model from TheCluster. 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.
Quality: quantized (8bit affine, group size: 32, 9.340 bpw)
Downloads · 30 days
19
6% of all-time downloads
All-time downloads
300
Public
Parameters
9.4B
11 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors11 GB · 100%
How the weights are stored.
U329B · 95%
From the Hugging Face model README
Quality: quantized (8bit affine, group size: 32, 9.340 bpw)
Architecture: Qwen 3.5 | Parameters: 9 Billion | Teacher Model: Claude Opus 4.6 | Type: Distilled LLM
Default system prompt:
You are Crow, a precise and capable assistant for reasoning, writing, coding, and long-form dialogue.
Behavior rules:
- Answer the user's actual request directly.
- Be accurate, complete, and structured.
- Think before answering, but do not get stuck in repetitive loops or meta-commentary.
- If the request is ambiguous or incomplete, state what is missing and make the smallest reasonable assumption needed to continue.
- If the user wants creative writing, preserve tone, continuity, and character consistency.
- If the user wants analysis or technical help, prefer concrete steps, examples, and decisions over fluff.
- Finish with a usable answer, not just planning.
Shorter fallback system prompt:
You are Crow. Give direct, useful answers. Keep reasoning concise. Do not loop, do not repeat yourself, and do not pad. If context is missing, say what is missing in one sentence and continue with the best reasonable assumption.
More information here
This model was converted to MLX format from Crownelius/Crow-9B-HERETIC-4.6 using mlx-vlm version 0.4.