GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
arsovskidev
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
arsovskidev
Model Tree
google/gemma-4-E4B-it
Input Modalities
Output Modalities
Supported Functionality
Standard Gemma 4 E4B is already solid. This fine-tune pushes it toward a more deliberate, structured reasoning style by training on ~2.3k high-quality Chain-of-Thought samples distilled from Claude 4.6 Opus.
The model learns to plan inside <think> tags before committing to a final
answer — fewer impulsive responses, more structured breakdowns.
text
<think>1. What is actually being asked here?2. What are the constraints and edge cases?3. Step-by-step plan...4. Verify the logic holds.</think> Final answer here.text
google/gemma-4-E4B-it │ ▼SFT + QLoRA 4-bit (Unsloth) │ loss masked to responses only ▼Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled │ ▼exported as GGUF (Q4_K_M + Q8_0)| Parameter | Value |
|---|---|
| Base model | google/gemma-4-E4B-it |
| Framework | Unsloth |
| Method | SFT + QLoRA (4-bit) |
| Dataset | nohurry/Opus-4.6-Reasoning-3000x-filtered |
| Hardware | RTX 5060 Ti 16GB |
| LoRA rank / alpha | 16 / 16 |
| Epochs | 3 |
| Max seq length | 2048 |
| Optimizer | adamw_8bit |
| Learning rate | 2e-4 |
| LR scheduler | cosine |
| Loss masking | train_on_responses_only |
| Dataset | Description |
|---|---|
| nohurry/Opus-4.6-Reasoning-3000x-filtered | ~2.3k filtered Claude 4.6 Opus reasoning trajectories covering math, logic, and coding |
Ollama:
bash
ollama run hf.co/arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilledllama.cpp:
bash
./llama-cli -hf arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled \ --temp 1.0 --top-p 0.95 --top-k 64Apache 2.0 + Gemma Terms of Use.
"Claude" is a trademark of Anthropic. This project is not affiliated with or endorsed by Anthropic — the name refers to the reasoning distillation data source only.
Unsloth for making this feasible on consumer hardware, and nohurry for the dataset.
bibtex
@misc{arsovskidev_gemma4_opus_distilled, title = {Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled}, author = {arsovskidev}, year = {2026}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled}}}<think>1. What is actually being asked here?2. What are the constraints and edge cases?3. Step-by-step plan...4. Verify the logic holds.</think>Final answer here.google/gemma-4-E4B-it │ ▼SFT + QLoRA 4-bit (Unsloth) │ loss masked to responses only ▼Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled │ ▼exported as GGUF (Q4_K_M + Q8_0)./llama-cli -hf arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled \ --temp 1.0 --top-p 0.95 --top-k 64@misc{arsovskidev_gemma4_opus_distilled, title = {Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled}, author = {arsovskidev}, year = {2026}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled}}}