| Model profile | ||
|---|---|---|
| Model | Size | Approximate size |
| Hy3Model source: provider262,144 tokens max native context | 295Bactive 21B | 177 GB4-bit quantization |
| Compatible hardware Estimated speeds, not benchmark results: calculated from memory bandwidth and model size. Real results can differ significantly because there is no precise formula for deriving LLM generation speed from hardware specifications alone. | ||||
|---|---|---|---|---|
| Hardware | Memory | Bandwidth | vLLM | Estimated generation |
| M5 Ultra | 256 GBUnified RAM | 1200 GB/s | no | 37 tok/s4-bit quantization |
| DGX H200 | 1128 GBGPU HBM3e | 4800 GB/s | yes | 129 tok/s4-bit quantization |
| DGX Station | 748 GBCoherent Memory | 7100 GB/s | yes | 174 tok/s4-bit quantization |
| ET900N G3 | 748 GBCoherent Memory | 7100 GB/s | yes | 174 tok/s4-bit quantization |
| DGX B200 | 1440 GBGPU HBM3e | 8000 GB/s | yes | 190 tok/s4-bit quantization |
| GB200 NVL72 | 13400 GBGPU HBM3e | 8000 GB/s | yes | 190 tok/s4-bit quantization |
| GB300 NVL72 | 20000 GBGPU HBM3e | 8000 GB/s | yes | 190 tok/s4-bit quantization |
Tests Laguna S 2.1's real-world coding capabilities and benchmarks performance against GLM 5.2, Qwen 3.7 Max, Hy3, and Kimi K3 using Woaibench.
Installs Colibri and demonstrates running Tencent Hy3 locally using disk, CPU and GPU resources.
Tests Tencent's 295B MoE Hy3 locally and in the cloud, comparing it against GLM 5.2 and Gemini 3.1 Pro to evaluate its performance levels.
Tests Tencent Hy3 295B MoE on 2x RTX PRO 6000 Blackwell GPUs using MXFP4 quantization via vLLM and SGLang for coding, agents, and real-world speed.
HY3 undergoes frontend coding, Three.js, HTML5 Canvas, and agentic programming tests, comparing code quality, speed, efficiency, reasoning, and visual output against Fable 5, Claude Opus 4.8, Claude S
Tests Hy3, a 295B MoE with 21B active parameters and 3.8B MTP layer parameters.
Tests Tencent HY3 against GLM and DeepSeek via browser OS, C++ skate game, Linux driver, skydiving, city timeline, frontend design, 3D model, and subway FPS evaluations.