GSAI-ML / text-generation updated 9 months ago

LLaDA-8B-Instruct

Name: LLaDA-8B-Instruct
Author: GSAI-ML

We introduce LLaDA, a diffusion model with an unprecedented 8B scale, trained entirely from scratch, rivaling LLaMA3 8B in performance.

Params

8.0 B

Context

—

Downloads 30d

429 K

Likes

359

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

Download history

daily snapshots · 10 days

429 K384 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	16.0 GB	19.3 GB	✅ Runs comfortably

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/llada-8b-instruct
{
  "hf_id": "GSAI-ML/LLaDA-8B-Instruct",
  "params_b": 8.02,
  "context_length": null,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 429004,
  "vram_estimates": [
    { "quant": "bf16", "gb": 19.3 }
  ],
  "updated_at": "2026-07-28T18:05:58Z"
}

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

Specifications

Architecture: LLaDAModelLM
Parameters: 8.0 B
Tensor type: BF16
Vocabulary: 126,464
Licence: mit
First seen on the Hub: 2025-02-19
Training datasets: undisclosed
Added to our catalog: 2026-07-28

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