Hunyuan 3
A long-context open model for agentic coding
Tencent’s open-weight 295B-parameter mixture-of-experts language model release, with 21B active parameters and a 256K-token context window, positioned for coding and agentic/tool-calling workflows.
Pricing
Model profile · Current snapshot
Input / 1M
$0.136
Output / 1M
$0.555
Blended / 1M
$0.241
Output TPS
82.24
TTFT (s)
1.89
Model Intelligence
Context window
256,000 tokens
Arena ranking
25
Benchmarkable
Yes
Model level
release
GPQA
0.9
HLE
0.34
SciCode
0.49
LCR
0.79
Recent stories
2 linked stories
releasePRIMARY2026-07-14
Tencent releases 1-bit and 4-bit GGUF weights for 295B Hy3 single-GPU runs
Tencent released 1-bit and 4-bit GGUF builds for its 295B Hy3 model with llama.cpp support and MTP. Posts cite 88–92GB local runs and SWE-Bench scores of 75.4% Verified and 53.9% Pro.
releasePRIMARY2026-07-06
Tencent releases Hy3, a 295B MoE model under Apache license
Tencent released Hy3 with 21B active parameters, a 256K context window, BF16/FP8 weights, and day-one vLLM/SGLang support. Kilo Code, Nous Portal, and OpenRouter also made it free for limited windows.