Downloads · 30 days
17
1% of all-time downloads
Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distill
meangrinch/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distill
Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distill is a machine learning model from meangrinch. Use it for the machine learning 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.
Fine-tuned reasoning model distilled from Claude 4.6 Opus chain-of-thought traces.
All-time downloads
1.3K
Public
Parameters
4.7B
9.3 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors9.3 GB · 100%
Parameter types
How the weights are stored.
BF164.7B · 100%
Base models
Model card
From the Hugging Face model README
Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distill
Fine-tuned reasoning model distilled from Claude 4.6 Opus chain-of-thought traces.
Training details
| Setting | Value |
|---|---|
| Dataset | opus_4.6_reasoning_1579x_filtered.jsonl |
| Method | SFTTrainer |
| LoRA Rank | rank=16, alpha=16 |
| Epochs | 3 |
| Warmup steps | 30 |
| Effective batch size | 16 |
| Learning rate | 1e-4 |
| Scheduler | cosine |
| Max sequence length | 4096 |
Source
- Base model: unsloth/Qwen3.5-4B
Related
- GGUF quantized version: Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distill-GGUF
- Type
- qwen3_5
- License
- apache-2.0
- Languages
- en
- Created
- Mar 10, 2026
- Updated
- Mar 15, 2026