Skip to content
localllm
日本語

tencent

Hy3

Parameters
295B
Max context length
262,144
Architecture
hy_v3
License
Commercial OK
Base model
tencent/Hy3
License
apache-2.0
llama.cpp
b9993+

About Hy3

Hy3 is a GGUF model based on tencent/Hy3 on Hugging Face. GGUF files are published by AngelSlim/Hy3-GGUF. It has about 295B parameters, the hy_v3 architecture, a maximum context length of 262,144 tokens (values written in the GGUF).

There are 4 quantizations, with file sizes from 89.4 GB (IQ1_M) to 185 GB (Q4_K_M) (actual sizes on Hugging Face).

Running Q4_K_M (182 GB) with an 8,192-token context needs an estimated 186 GB of memory, and an estimated 194 GB at 32,768 tokens. For 8,192 tokens, a GPU with 192 GB or more of VRAM, or a Mac with 192 GB or more of unified memory, is a rough guide (macOS caps how much memory the GPU can use, so leave some headroom). The smallest, IQ1_M (89.4 GB), needs an estimated 92.9 GB at 8,192 tokens.

The original model is licensed under Apache License 2.0, which allows commercial use (keep the license text and copyright notice when redistributing). Check the original license for the terms of use.

File size and estimated memory per quantization

  • Up to 8 GB
  • Up to 16 GB
  • Up to 24 GB
  • Up to 48 GB
  • Up to 128 GB
  • More

File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.

All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).

About the "quality guide" (how far a quantization drifts from the original)

For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.

The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).

These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".

Quantization Quality guide KLD (no imatrix) KLD (imatrix) Size (Llama-3-8B)
Q8_0 Nearly identical 0.0014 - 7.96 GiB
Q6_K Very small 0.0055 - 6.14 GiB
Q5_K_M Very small 0.0108 - 5.33 GiB
Q5_K_S Small 0.0166 - 5.21 GiB
Q5_1 Small 0.0180 - 5.65 GiB
Q5_0 Small 0.0222 - 5.21 GiB
Q4_K_M Small 0.0313 0.0282 4.58 GiB
Q4_K_S Medium 0.0431 0.0320 4.37 GiB
IQ4_NL Small - 0.0357 4.35 GiB
IQ4_XS Small - 0.0363 4.14 GiB
Q4_1 Medium 0.0717 - 4.78 GiB
Q4_0 Medium 0.0719 - 4.34 GiB
Q3_K_L Medium 0.0872 0.0731 4.03 GiB
Q3_K_M Medium 0.1019 0.0844 3.74 GiB
IQ3_M Medium - 0.1025 3.53 GiB
IQ3_S Medium - 0.1113 3.42 GiB
IQ3_XS Large - 0.1387 3.28 GiB
IQ3_XXS Large - 0.1836 3.05 GiB
Q3_K_S Large 0.2282 0.1998 3.41 GiB
IQ2_M Large - 0.3260 2.74 GiB
Q2_K Very large 0.4451 0.3322 2.96 GiB
Q2_K_S Very large - 0.4034 2.96 GiB
IQ2_S Very large - 0.4392 2.56 GiB
IQ2_XS Very large - 0.5463 2.43 GiB
IQ2_XXS Very large - 0.8120 2.24 GiB
IQ1_M Very large - 1.3931 2.01 GiB
IQ1_S Very large - 2.2546 1.88 GiB

Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations

GGUF source

AngelSlim/Hy3-GGUF

Converted and published by a third party About this label

Last checked: Nov 11, 2026

Architecture
hy_v3
llama.cpp b9993 and later
Parameters
295.0B
Max context length
262,144
License
apache-2.0 Commercial OK
File size and memory per quantization for Hy3 (AngelSlim/Hy3-GGUF)
Quantization File size Measured Quality guide 4,096 8,192 16,384 32,768 65,536 131,072 262,144 max
IQ1_M Hy3-IQ1_M 89.4 GB Very large 91.6 GB 92.9 GB 95.6 GB 101 GB 112 GB 133 GB 176 GB
IQ1_M Hy3-IQ1_M-mtp 91.8 GB Very large 93.9 GB 95.2 GB 97.9 GB 103 GB 114 GB 135 GB 178 GB
Q2_K_XL Hy3-Q2_K_XL 100 GB - 102 GB 104 GB 106 GB 112 GB 122 GB 144 GB 187 GB
Q2_K_XL Hy3-Q2_K_XL-mtp 102 GB - 104 GB 105 GB 108 GB 113 GB 124 GB 145 GB 188 GB
Q3_K_M Hy3-Q3_K_M 135 GB Medium 137 GB 138 GB 141 GB 146 GB 157 GB 178 GB 221 GB
Q3_K_M Hy3-Q3_K_M-mtp 136 GB Medium 139 GB 140 GB 143 GB 148 GB 159 GB 180 GB 223 GB
Q4_K_M Hy3-Q4_K_M 182 GB Small 184 GB 186 GB 188 GB 194 GB 205 GB 226 GB 269 GB
Q4_K_M Hy3-Q4_K_M-mtp 185 GB Small 187 GB 188 GB 191 GB 196 GB 207 GB 228 GB 271 GB 
Ollama  ollama run hf.co/AngelSlim/Hy3-GGUF:Q4_K_M
llama.cpp  llama-server -hf AngelSlim/Hy3-GGUF:Q4_K_M

Third-party evaluations

Values from other organizations for the original model before quantization. Not this site's own rating. Values are for the original model before quantization. GGUF quantization (especially small quantizations) can lower performance.

Human preference (LMArena)

1,454 1,449–1,460

hy3 · 15,068 votes · Values as of Nov 9, 2026

Source: LMArena (CC BY 4.0). Original leaderboard · See in ranking

License and commercial use

Apache License 2.0 Commercial OK

Allows commercial use, modification and redistribution. When redistributing, keep the license text and copyright notice, and note changes in modified files.

Based on the license on the original model's Hugging Face page. Original license text (checked Oct 18, 2026)

The summary states facts this site read from the original text and is not legal advice. Always check the original license and its latest terms before use. All licenses

How to run

Mainline llama.cpp can load this model's format (hy_v3) from b9993 (Jul 14, 2026) onward. Ollama and LM Studio bundle llama.cpp internally, so an older app fails to load it with errors such as "unknown model architecture". If that happens, update the app.

Example commands using Q4_K_M. To use another quantization, replace the name with one from the table above. How to run local LLMs

Ollama

Run it by pointing directly at the GGUF on Hugging Face.

ollama run hf.co/AngelSlim/Hy3-GGUF:Q4_K_M

llama.cpp

Pass the repository and quantization name to llama-server (or llama-cli) with -hf.

llama-server -hf AngelSlim/Hy3-GGUF:Q4_K_M

LM Studio

Paste AngelSlim/Hy3-GGUF into the search box, download it, and choose the quantization from the file list.

Frequently asked questions

How much memory do I need to run Hy3 (Q4_K_M)?
The file size is 182 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 186 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
Can Hy3 be used commercially?
The original model's license is Apache License 2.0 (Commercial use allowed).Allows commercial use, modification and redistribution. When redistributing, keep the license text and copyright notice, and note changes in modified files. Check the original license text before deciding.
Does Hy3 run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?
8 GB: no quantization fits; 12 GB: no quantization fits; 16 GB: no quantization fits; 24 GB: no quantization fits (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).
What is the command to run Hy3 with Ollama?
Run "ollama run hf.co/AngelSlim/Hy3-GGUF:Q4_K_M" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.