deepseek-ai / text-generation Open weights updated 1 year ago

DeepSeek-R1-Distill-Qwen-7B

Name: DeepSeek-R1-Distill-Qwen-7B
Author: deepseek-ai

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. However, DeepSeek-R1-Zero encounters chall...

Params

7.6 B

Context

131,072

Downloads 30d

322 K

Likes

956

Commercial use: allowed mit Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 18 K in the last 30 days (6.1%)

387 K245 K

Jul 28Sep 1Oct 6Nov 10

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	15.2 GB	18.4 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 128K ctx	15.2 GB	35.5 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/deepseek-r1-distill-qwen-7b
{
  "hf_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
  "params_b": 7.62,
  "context_length": 131072,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 321610,
  "vram_estimates": [
    { "quant": "bf16", "gb": 18.4 }
  ],
  "updated_at": "2026-07-28T18:06:49Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: Qwen2ForCausalLM
Parameters: 7.6 B
Tensor type: BF16
Context length: 131,072
Vocabulary: 152,064
Layers / heads: 28 / 28
Licence: mit
First seen on the Hub: 2025-01-20
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Derivative DeepSeek-R1-Distill-Qwen-7B-GGUF bartowski 139 K

Compare with any text-generation model

Popular comparisons

Qwen3-14B 12.9 M Qwen3-8B 6.8 M Qwen2.5-7B-Instruct 6.0 M gpt-oss-20b 5.8 M Llama-3.1-8B-Instruct 4.5 M Qwen3-4B 4.0 M