Similar Models

Jackrong/Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

A 2B dense architecture model fine-tuned with structured step-by-step reasoning trajectories distilled from Claude 4.6 Opus.

reasoningchain-of-thoughtqwen

distil-labs/distil-qwen3-4b-text2sql-gguf

New

Task-specialized 4B model for natural-language-to-SQL conversion. Distilled from DeepSeek-V3. Quantized GGUF for local database agents.

text2sqltask-specializeddistilled

← Back to Models

DeepSeek R1 Distill (Qwen 7B)

deepseek/r1-distill-qwen-7b

A 2026-native reasoning model distilled from R1. Specialized for agentic "Chain of Thought" logic on local hardware.

How to Use

To get started, install the `transformers` library:

pip install transformers

Then, use the following snippet to load the model:

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "deepseek/r1-distill-qwen-7b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

# Your inference code here...

Available Versions

Tag / Variant	Size	Format	Download
deepseek/r1-distill-qwen-7b:Q4_K_M	4.9GB	GGUF	Link

Model Details

Teacher Model

DeepSeek-R1-Full

Distillation Method

Knowledge Distillation (Logits)

Training Dataset

Flickr30k (Conceptual)

Primary Task

Multimodal Generation

Performance Metrics (Example)

Metric	Student Model	Teacher Model
Model Size	4.9GB	8.5GB
BLEU Score	28.5	30.1