LLaDA2.0-mini
LLaDA2.0-mini is a diffusion language model featuring a 16BA1B Mixture-of-Experts (MoE) architecture. As an enhanced, instruction-tuned iteration of the LLaDA series, it is optimized for practical applications.
Params
16.3 B
Context
32,768
Downloads 30d
230 K
Likes
71
Download history
daily snapshots · 27 days236 K184 K
Aug 26Sep 4Sep 13Sep 21
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 | 32.5 GB | 38.7 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 32K ctx | 32.5 GB | 46.0 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 -s https://aimodelscomparison.com/api/v1/models/llada2-0-mini
{
"hf_id": "inclusionAI/LLaDA2.0-mini",
"params_b": 16.26,
"context_length": 32768,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 230110,
"vram_estimates": [
{ "quant": "bf16", "gb": 38.7 }
],
"updated_at": "2026-08-26T01:00:44Z"
}
Specifications
- Architecture
- LLaDA2MoeModelLM
- Parameters
- 16.3 B
- Tensor type
- BF16
- Context length
- 32,768
- Vocabulary
- 157,184
- Layers / heads
- 20 / 16
- Licence
- apache-2.0
- First seen on the Hub
- 2025-11-25
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-26
Compare with any text-generation model