Downloads · 30 days
657
35% of all-time downloads
khazarai/Qwen3.5-9B-Kimi-k3-Distilled-GGUF
Qwen3.5-9B-Kimi-k3-Distilled-GGUF is a image-text-to-text model from khazarai. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Qwen3.5-9B-Kimi-k3-Distilled is a fine-tuned, reasoning-focused model derived from the Qwen architecture via knowledge distillation from Kimi K3 (moonshotai/kimi-k3).
Downloads · 30 days
657
35% of all-time downloads
All-time downloads
1.9K
Public
Repo size
27.4 GB
Likes
3
Public
Click a slice to open those files.
.gguf27.4 GB · 100%
From the Hugging Face model README
Qwen3.5-9B-Kimi-k3-Distilled is a fine-tuned, reasoning-focused model derived from the Qwen architecture via knowledge distillation from Kimi K3 (moonshotai/kimi-k3).
Unlike standard instruction-tuned models that heavily rely on speculative internal chain-of-thought hallucination, this model is explicitly optimized for environment-grounded agentic workflows. It natively integrates reasoning with tool execution, prioritizing direct environment interaction (e.g., executing shell commands, listing files, reading logs) over ungrounded hypothetical reasoning loops.
This model is designed primarily for:
The dataset consists of behaviour-preserving instruction-following, tool-use, and agent trajectories distilled from Kimi K3 (moonshotai/kimi-k3).
The training trajectory drop includes multi-language code contexts, scripts, and tool calls across:
Python, TypeScript, English, Go, Bash, C, C#, Java, C++, Ruby, Assembly, PowerShell, Rust, and general technical plain text (unknown).
The training trajectory mix emphasizes structural tool integration rather than static QA:
ls, grep, cat, repo navigation).During internal evaluations comparing Qwen3.5-9B against Qwen3.5-9B-Kimi-k3-Distilled on agentic/coding benchmarks:
| Model | Grounded Tool Call Rate | Speculative Hallucination Rate | Task Completion Efficiency |
|---|---|---|---|
| Qwen3.5-9B (Base) | Low (tends to guess) | High (long hypothetical text chains) | Sub-optimal in agent loops |
| Qwen3.5-9B-Kimi-k3-Distilled | High (Immediate Execution) | Low (Action-driven reasoning) | High (Fast convergence) |
release.sh) in a workspace.bash tool call (ls -la / cat release.sh) to inspect the real file before drawing conclusions.