Check my GPU

LLMs ·

Hunyuan Hy3 (295B-A21B)

Parameters
299B (21.0B active)
Architecture
Mixture of experts
Max context
256K tokens
License
apache-2.0
Released
2026-07

How to run it

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/bartowski/Hy3-GGUF (opens in a new tab)

ollama run hf.co/bartowski/Hy3-GGUF

Original weights · Hugging Face

Full-precision files from Tencent, for fine-tuning, vLLM, Transformers.

huggingface.co/tencent/Hy3 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Tencent. The weights themselves download from Hugging Face.

github.com/Tencent-Hunyuan/Hy3 (opens in a new tab)

git clone https://github.com/Tencent-Hunyuan/Hy3

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 120 GB 123 GB 131 GB GGUF · folder (opens in a new tab)
Q3_K_M Low 146 GB 150 GB 158 GB GGUF · folder (opens in a new tab)
Q4_K_M Good 182 GB 186 GB 194 GB GGUF · folder (opens in a new tab)
Q5_K_M High 212 GB 215 GB 223 GB GGUF · folder (opens in a new tab)
Q6_K High 245 GB 248 GB 256 GB GGUF · folder (opens in a new tab)
Q8_0 Very high 317 GB 320 GB 328 GB GGUF · folder (opens in a new tab)
F16 Full 598 GB 601 GB 609 GB Original weights (opens in a new tab)

Best hardware for Hunyuan Hy3 (295B-A21B)

Grade · points Hardware Quant Memory Speed Fit
89 ptsExcellent (S) · 89 of 100 points: Model quality 40.4/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 13.0/15 Apple M3 Ultra (512 GB) Q4_K_M 216 GB / 384 GB 20.6 tok/s Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 35.7/45, Memory fit 24.0/25, Speed 12.2/15, Memory use 15.0/15 Apple M3 Ultra (256 GB) Q3_K_M 165 GB / 192 GB 26.6 tok/s Tight fit
82 ptsGreat (A) · 82 of 100 points: Model quality 29.7/45, Memory fit 24.0/25, Speed 13.6/15, Memory use 15.0/15 Apple M2 Ultra (192 GB) Q2_K 134 GB / 144 GB 33.1 tok/s Tight fit

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.