Skip to content
Weights Not Walls
Menu

tencent

Hy4-preview

Reviewed
Size
780B parameterscounted from the safetensors header on the Hub
Licence
unknown, Apache License 2.0Our reading, check the licence: You can use, change and redistribute the model, including commercially. Keep the licence and any notices, and say which files you changed; you do not have to publish your changes. It includes a patent licence that ends for anyone who sues over patents in the work.
On the Hub since
27 Aug 2026the date the repo was created
Context length
1M tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)HYV4ForCausalLM
On Hugging Face
tencent/Hy4-preview11k downloads in the last 30 days, 565 likes

Scores

2 independent results on 2 eval sets
GDP.pdfReported

Epoch's name: hy4-preview. Best closed model on this set: gemini-4-carbon_high, 56.4% (Google DeepMind). All 19 results

ProofBenchReported

Epoch's name: hy4-preview. Best closed model on this set: claude-fable-5-1_max, 100.0% (Anthropic). All 85 results

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.69 GB, worked out from the model's config (tencent/Hy4-preview), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

6block/Hy4-preview-GGUF (converted by 6block), 543 downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
IQ2_XS219.0 GBfile size, 39 parts220.1 GB219.0 + 0.69 + 0.50
Commands
llama.cpp
llama-server -hf 6block/Hy4-preview-GGUF:IQ2_XS
Download
hf download 6block/Hy4-preview-GGUF --include "Hy4-preview-IQ2_XS-*-of-00039.gguf" --local-dir Hy4-preview-GGUF
Q2_K269.7 GBfile size, 39 parts270.8 GB269.7 + 0.69 + 0.50
Commands
llama.cpp
llama-server -hf 6block/Hy4-preview-GGUF:Q2_K
Download
hf download 6block/Hy4-preview-GGUF --include "Hy4-preview-Q2_K-*-of-00039.gguf" --local-dir Hy4-preview-GGUF
IQ4_XS388.3 GBfile size, 39 parts389.5 GB388.3 + 0.69 + 0.50
Commands
llama.cpp
llama-server -hf 6block/Hy4-preview-GGUF:IQ4_XS
Download
hf download 6block/Hy4-preview-GGUF --include "Hy4-preview-IQ4_XS-*-of-00039.gguf" --local-dir Hy4-preview-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 4bitmlx-community/Hy4-preview-4bit403.6 GBfile size404.8 GB403.6 + 0.69 + 0.50Download page

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights1452.8 GBfile size1454.0 GB1452.8 + 0.69 + 0.50
hf download tencent/Hy4-preview --local-dir Hy4-preview
Other conversions (3; sizes not read)

The Hub tags 5 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

5 providers serve this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.

ProviderInOutContextPrecisionTokens/sFirst tokenUptime 24hToolsJSON
DeepInfra$0.83$2.501Mfp4452.6 s100.0%yesyes
Novita$0.83$2.50977kfp8395.1 s100.0%yesyes
SiliconFlow$0.83$2.501Mfp8541.9 s100.0%yesyes
Tencentthe maker$0.83$2.501Mfp8303.2 s100.0%yesyes
Venice$1.04$3.131Mfp4451.4 s100.0%yesyes

Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.

curl https://router.huggingface.co/v1/chat/completions \ -H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \ -d '{"model": "tencent/Hy4-preview:deepinfra", "messages": [{"role": "user", "content": "Hello"}]}'

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.