Hunyuan-A13B-Instruct
🤗 Hugging Face 🖥️ Official Website 🕖 HunyuanAPI 🕹️ Demo 🤖 ModelScope
Params
80.4 B
Context
32,768
Downloads 30d
69 K
Likes
795
Download history
tracking started — chart appears after 7 days of snapshots (6 recorded)69 K downloads in the last 30 days
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 | 160.8 GB | 189.4 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 32K ctx | 160.8 GB | 225.6 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/hunyuan-a13b-instruct
{
"hf_id": "tencent/Hunyuan-A13B-Instruct",
"params_b": 80.39,
"context_length": 32768,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 68873,
"vram_estimates": [
{ "quant": "bf16", "gb": 189.4 }
],
"updated_at": "2026-10-19T06:00:53Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.14
input / 1M
$0.57
output / 1M
—
cached input / 1M
$0.71
1M in + 1M out
- Context window
- 131,072 tokens
- Max output
- 117,964 tokens
- Providers
- 1
- Cheapest provider
- SiliconFlow · $0.14 / $0.57
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / — / —
✗ Tool calling
✓ Reasoning
✓ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✗ Prompt caching
Specifications
- Architecture
- HunYuanMoEV1ForCausalLM
- Parameters
- 80.4 B
- Tensor type
- BF16
- Context length
- 32,768
- Vocabulary
- 128,167
- Layers / heads
- 32 / 32
- Licence
- other
- First seen on the Hub
- 2025-06-25
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model