Hy3
- Model Introduction - Stronger Agent Capabilities - More Reliable Product Experiences - Benchmark Appendix - News - Model Links - Quickstart - Deployment - vLLM - SGLang - Finetuning - RL Post-training - Quantization - License - Contact Us
Params
298.8 B
Context
262,144
Downloads 30d
798 K
Likes
986
Download history
daily snapshots · 25 days798 K188 K
Sep 29Oct 7Oct 15Oct 23
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 | 597.6 GB | 702.7 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 597.6 GB | 2,092.0 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/hy3
{
"hf_id": "tencent/Hy3",
"params_b": 298.79,
"context_length": 262144,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 797888,
"vram_estimates": [
{ "quant": "bf16", "gb": 702.7 }
],
"updated_at": "2026-09-29T01:00:12Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-23$0.13
input / 1M
$0.53
output / 1M
$0.033
cached input / 1M
$0.66
1M in + 1M out
Price tiers
- Daily 16:00–00:00 UTC: input $0.083/M, output $0.33/M (0.63× base)
- Context window
- 262,144 tokens
- Max output
- 128,000 tokens
- Providers
- 5
- Cheapest provider
- Tencent · $0.13 / $0.53
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / — / —
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- HYV3ForCausalLM
- Parameters
- 298.8 B
- Tensor type
- BF16
- Context length
- 262,144
- Vocabulary
- 120,832
- Layers / heads
- 80 / 64
- Licence
- apache-2.0
- First seen on the Hub
- 2026-07-02
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-29
Compare with any text-generation model
Popular comparisons
Appears in