Hy4 Base
- In Input modalities: TextImage
- Open weights
Prices
0 offerings · prices as listedNo priced offering is listed for this model yet.
Details
- Licence
- tencent-hy-license
- Family
- hy-base
Run locally
Weights: tencent/Hy4-base- Parameters 771.1B
- Active 50.3B (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)
- Needs
- ≈ 401.3 GB (weights 381.5 + KV cache 0.7 + overhead 19.1)
- 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) | 1436.4 GB | ≈ 1508.9 | ✕Doesn’t fit | — |
| Q8_0 | 763.1 GB | ≈ 801.9 | ✕Doesn’t fit | — |
| FP8 | 718.2 GB | ≈ 754.8 | ✕Doesn’t fit | — |
| Q6_K | 589.8 GB | ≈ 620.0 | ✕Doesn’t fit | — |
| Q5_K_M | 510.8 GB | ≈ 537.0 | ✕Doesn’t fit | — |
| Q5_0 | 493.8 GB | ≈ 519.1 | ✕Doesn’t fit | — |
| Q4_K_M | 436.3 GB | ≈ 458.8 | ✕Doesn’t fit | — |
| Q4_0 | 404.0 GB | ≈ 424.9 | ✕Doesn’t fit | — |
| IQ4_XS | 381.5 GB | ≈ 401.3 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 351.0 GB | ≈ 369.2 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 274.7 GB | ≈ 289.1 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 269.3 GB | ≈ 283.5 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 184.9 GB | ≈ 194.9 | ✕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 usThis model isn’t on any leaderboard we cite yet.
Changes
All changes →- New language model
Sources
- tencent/Hy4-base config.json (opens in a new tab) huggingface.co · checked Nov 20, 2026
- tencent/Hy4-base model card (opens in a new tab) huggingface.co · checked Nov 20, 2026
- tencent/Hy4-base model card (opens in a new tab) huggingface.co · checked Nov 20, 2026
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Tencent · China · tencent.com
Related models
Snapshots, the same family and other models from this provider