unsloth/Phi-4-mini-reasoning-GGUF
NewMicrosoft Phi-4-mini distilled for step-by-step reasoning. 3.8B params, 128K context, MIT license. Unsloth bug-fixed GGUF for reliable agentic tool-calling.
reasoningagentictool-calling
Analytics loading...
Similar Models
Jackrong/Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled-GGUF
NewA 2B dense architecture model fine-tuned with structured step-by-step reasoning trajectories distilled from Claude 4.6 Opus.
reasoningchain-of-thoughtqwen
unsloth/Qwen3.5-0.8B-GGUF
NewAlibaba Qwen3.5 sub-1B via Unsloth Dynamic 2.0. 256K context, Apache 2.0. Optimized for lightweight function-calling agents and document parsing workflows.
ultra-smalllong-contextfunction-calling
Qwopus3.5-4B-v3 (Act-Then-Refine Agent)
Jackrong/Qwopus3.5-4B-v3-GGUF
Reasoning-enhanced Qwen3.5-4B fine-tuned for "act-then-refine" agentic workflows. Tool-calling RL, structural reasoning optimization, HumanEval 75.61%.
How to Use
To get started, install the `transformers` library:
pip install transformersThen, use the following snippet to load the model:
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "Jackrong/Qwopus3.5-4B-v3-GGUF"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
# Your inference code here...Available Versions
Model Details
Teacher Model
Qwen/Qwen3.5-4B
Distillation Method
Knowledge Distillation (Logits)
Training Dataset
Flickr30k (Conceptual)
Primary Task
Multimodal Generation
Performance Metrics (Example)
| Metric | Student Model | Teacher Model |
|---|---|---|
| Model Size | 2.71GB | 8.5GB |
| BLEU Score | 28.5 | 30.1 |