Hy4 Preview
- In Input modalities: Text Out Output modalities: Text
- Reasoning· none, high
- Reasoning can be off
- Tool use
- Structured output
- Open weights
Prices
2 offerings · prices as listed| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | ¥6.00 | ¥0.30 | ¥18.00 |
| Batch | ¥3.00 | ¥0.15 | ¥9.00 |
Prices from 腾讯云 TokenHub:模型价格 (opens in a new tab) (checked Nov 5, 2026)
| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | ¥6.00 | ¥0.30 | ¥18.00 |
| Batch | ¥3.00 | ¥0.15 | ¥9.00 |
Prices from 腾讯云 TokenHub:模型价格 (opens in a new tab) (checked Nov 5, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Max input
- 960K
- Licence
- Apache License 2.0
- Family
- hy
- Model ID
Not stated on Tencent’s pages: max thinking budget, built-in tools, knowledge cutoff, aliases.
Run locally
Weights: tencent/Hy4-preview- Parameters 780B
- Active 49.7B (estimated) · 256 experts, 8 per token
- Native precision BF16
- Layers 78
- KV cache per token 88 KB
- Config positions 1024K (config.json max_position_embeddings)
- API context 1000K (maker’s API)
- Needs
- ≈ 405.9 GB (weights 385.9 + KV cache 0.7 + overhead 19.3)
- Usable
- 21.6 GB (90% of its memory)
- Try
- it’s too large for this hardware; see the smallest that runs it below
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 1452.8 GB | ≈ 1526.2 | ✕Doesn’t fit | — |
| Q8_0 | 771.8 GB | ≈ 811.1 | ✕Doesn’t fit | — |
| FP8maker’s file | 757.9 GB | ≈ 796.5 | ✕Doesn’t fit | — |
| Q6_K | 596.6 GB | ≈ 627.1 | ✕Doesn’t fit | — |
| Q5_K_M | 516.6 GB | ≈ 543.2 | ✕Doesn’t fit | — |
| Q5_0 | 499.4 GB | ≈ 525.1 | ✕Doesn’t fit | — |
| Q4_K_M | 441.3 GB | ≈ 464.0 | ✕Doesn’t fit | — |
| Q4_0 | 408.6 GB | ≈ 429.7 | ✕Doesn’t fit | — |
| IQ4_XS | 385.9 GB | ≈ 405.9 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 355.0 GB | ≈ 373.5 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 277.8 GB | ≈ 292.4 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 272.4 GB | ≈ 286.7 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 187.0 GB | ≈ 197.1 | ✕Doesn’t fit | — |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): no single listed machine; about 7 × 80 GB GPUs.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-21. How it’s estimated
Cited scores
From third-party leaderboards, not measured by us- LMArena WebDev 1,632
#21 of 94 listed models · CI 1,622–1,642 · 4,599 votes
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Nov 8, 2026
- changes we made
News
All news →- Aug 28, 2026Release Tencent releases Hy4 Preview Preview 1.02M-token context window. On Tencent Cloud TokenHub: ¥6.00 input, ¥18.00 output per 1M tokens.
Changes
All changes →- 3 new prices on Tencent Cloud TokenHub, China Input (Batch) ¥3.00 · Output (Batch) ¥9.00 · Cache read (Batch) ¥0.15
- Now priced on Tencent Cloud TokenHub, China Input ¥6.00 · Output ¥18.00 · Cache read ¥0.30 · Input (Batch) ¥3.00 · +2 more
- Now priced on Tencent Cloud TokenHub, China Input ¥6.00 · Output ¥18.00 · Cache read ¥0.30
- 3 new prices on Tencent Cloud TokenHub, China Input (Batch) ¥3.00 · Output (Batch) ¥9.00 · Cache read (Batch) ¥0.15
- New language model
- New language model
Sources
- 腾讯云 TokenHub:模型价格in Chinese (opens in a new tab) cloud.tencent.com · checked Nov 5, 2026
- 腾讯云 TokenHub:混元调用指南in Chinese (opens in a new tab) cloud.tencent.com · checked Nov 9, 2026
- tencent/Hy4-preview on Hugging Face (Tencent) (opens in a new tab) huggingface.co · checked Nov 8, 2026
- Tencent Releases and Open-Sources Tencent Hy4 preview - Tencent (opens in a new tab) tencent.com · checked Nov 8, 2026
- tencent/Hy4-preview model card (opens in a new tab) huggingface.co · checked Nov 8, 2026
- 模型列表in Chinese (opens in a new tab) intl.cloud.tencent.com · checked Nov 7, 2026
- 深度思考in Chinese (opens in a new tab) intl.cloud.tencent.com · checked Nov 5, 2026
- tencent/Hy4-preview model card (opens in a new tab) huggingface.co · checked Nov 6, 2026
- tencent/Hy4-preview config.json (opens in a new tab) huggingface.co · checked Nov 7, 2026
- tencent/Hy4-preview files (opens in a new tab) huggingface.co · checked Nov 9, 2026
- tencent/Hy4-preview-FP8 files (opens in a new tab) huggingface.co · checked Nov 6, 2026
- 大模型服务平台 TokenHub 模型列表_腾讯云in Chinese (opens in a new tab) cloud.tencent.com · checked Nov 5, 2026
- Tencent Releases and Open-Sources Tencent Hy4 preview - Tencent (opens in a new tab) tencent.com · checked Nov 5, 2026
Tencent · China · tencent.com
Related models
Snapshots, the same family and other models from this provider