LocalClaw/LLM/Hy3
Open-weight local LLM

Hy3

Use case: Coding assistant. Check the memory fit and choose a setup path below.

128 GB catalogue minimum128 GB RAMIQ1_MCoding assistant
Choose an app

This is an advanced workstation/server GGUF path. Unsupported apps are clearly marked.

Compare models
LM StudioNot available for this model
Open in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloadsOpen llama.cpp setupAdvanced option: opens GGUF files and patch notesUse with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
295B (21B active)
Minimum RAM
128 GB
Model size
89 GB
Quantization
IQ1_M

About Hy3

Catalogue summary: Tencent Hy Team MoE model with 256K context, strong agent/productivity benchmarks and Apache 2.0 licensing. Practical only for very large local workstations via IQ1_M GGUF.

Hy3 has a catalogue minimum of 128 GB RAM with IQ1_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Treat hy3 as an advanced workstation/server-grade catalogue target with verified GGUF artefacts. Open the GGUF files and follow the upstream runtime notes; LocalClaw does not claim a one-click LM Studio install.

Model sourcePublic GGUF repository (verified 2026-11-06): AngelSlim/Hy3-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningbeasttool-callinggeneral

Deployment path

01
Check RAM fitServer-grade target. Plan for 128 GB class multi-GPU memory.
02
Load the modelOpen the verified GGUF files for hy3 and follow the upstream runtime or patch notes first.
03
Try your workloadStart with a short prompt, check memory use and adjust context length before running longer tasks.

Catalogue record

  • Family: hy3
  • Parameters: 295B (21B active)
  • Recommended quantization: IQ1_M
  • Catalogue minimum RAM: 128 GB
  • Catalogue model size: 89 GB
  • Tags: chat, code, reasoning, beast, tool-calling, general

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Reading the scores

LocalClaw /10 is an editorial catalogue rating. Community /5 comes from member reviews. Your machine fit is a separate memory and runtime assessment.

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
2
quality
9
coding
9
reasoning
9

Technical notes

Developer
Tencent Hy Team
License
Apache 2.0
Context window
262,144 tokens
Architecture
Sparse Mixture-of-Experts model with 295B total parameters, 21B active parameters, 192 experts, top-8 routing and an MTP layer.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Large unified memoryMac Studio M4 Max 128GB128GB AI PC classNVIDIA GB10 / DGX SparkHigh-memory picks128GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

GPT-OSS (120B) 117B (5.1B active)Laguna S 2.1 118B (8B active, MoE)GLM-5.3-Flash 320B (18B active, MoE)K2-Horizon-MoVA-36B-A4B 36B (4B active, MoE)MiMo-V2.6-Flash-RL 309B (15B active, MoE)Qwen3.8 Flash Next 125B + 51B n-gram (6B active)DeepSeek V4 Flash Vision Exp 284B (13B active, multimodal MoE)Ling Flash Base 2.0 106B (6.1B active, MoE)

Where to go next