deepseek-ai / text-generation updated 1 year ago

DeepSeek-R1-Distill-Llama-70B

Name: DeepSeek-R1-Distill-Llama-70B
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

70.6 B

Context

131,072

Downloads 30d

512 K

Likes

794

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

Download history

daily snapshots · 10 days

750 K512 K

Jul 28Jul 31Aug 3Aug 6

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	141.1 GB	166.3 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 128K ctx	141.1 GB	325.0 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-llama-70b
{
  "hf_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
  "params_b": 70.55,
  "context_length": 131072,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 512372,
  "vram_estimates": [
    { "quant": "bf16", "gb": 166.3 }
  ],
  "updated_at": "2026-07-28T18:04:10Z"
}

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

Specifications

Architecture: LlamaForCausalLM
Parameters: 70.6 B
Tensor type: BF16
Context length: 131,072
Vocabulary: 128,256
Layers / heads: 80 / 64
Licence: mit
First seen on the Hub: 2025-01-20
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3.6-35B-A3B-NVFP4 11.3 M gpt-oss-20b 8.6 M Qwen3-32B 8.3 M dolphin-2.9.1-yi-1.5-34b 4.6 M gpt-oss-120b 4.2 M NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 2.8 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB