🪶 CROW-9B

Flagship Intelligence. Featherweight Footprint. Meticulously distilled from Claude Opus 4.6 into a highly efficient Qwen 3.5 architecture.

Architecture: Qwen 3.5 | Parameters: 9 Billion | Teacher Model: Claude Opus 4.6 | Type: Distilled LLM

Distilled Excellence: Captures the deep reasoning, nuanced formatting, and instruction-following capabilities of Claude Opus 4.6.
Highly Agile: At just 9B parameters, Crow runs efficiently on consumer-grade GPUs and edge devices without sacrificing contextual depth.
Qwen 3.5 Backbone: Inherits robust multilingual support, a massive context window, and structural stability.

Available Model files:

Qwen3.5-9B-heretic-v2.F16.gguf
Qwen3.5-9B-heretic-v2.Q8_0.gguf
Qwen3.5-9B-heretic-v2.Q5_K_M.gguf
Qwen3.5-9B-heretic-v2.Q4_K_M.gguf
Qwen3.5-9B-heretic-v2.BF16-mmproj.gguf This was trained 2x faster with Unsloth

Safetensors

Model size

9B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Base model

Finetuned

Quantized

(3)

this model