deepseek-ai / text-generation updated 1 year ago

DeepSeek-R1-0528-Qwen3-8B

Name: DeepSeek-R1-0528-Qwen3-8B
Author: deepseek-ai

The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528. In the latest update, DeepSeek R1 has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark e...

Params

8.2 B

Context

131,072

Downloads 30d

1.7 M

Likes

1,082

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

Download history

daily snapshots · 10 days

2.0 M1.7 M

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	16.4 GB	19.7 GB	⚠️ Tight — reduce context
model.safetensors (bf16, full)	bf16 + 128K ctx	16.4 GB	38.2 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-r1-0528-qwen3-8b
{
  "hf_id": "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
  "params_b": 8.19,
  "context_length": 131072,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 1710996,
  "vram_estimates": [
    { "quant": "bf16", "gb": 19.7 }
  ],
  "updated_at": "2026-07-28T17:08:10Z"
}

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

Specifications

Architecture: Qwen3ForCausalLM
Parameters: 8.2 B
Tensor type: BF16
Context length: 131,072
Vocabulary: 151,936
Layers / heads: 36 / 32
Licence: mit
First seen on the Hub: 2025-05-29
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Derivative DeepSeek-R1-0528-Qwen3-8B-MLX-4bit lmstudio-community 285 K Derivative DeepSeek-R1-0528-Qwen3-8B-MLX-8bit lmstudio-community 264 K

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-7B-Instruct-AWQ 4.6 M granite-4.1-8b 4.2 M

Appears in

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