Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI researchers, ML researchers, agent developers, AI infrastructure teams, founders, engineering teams, applied scientists, AI-curious readers, automation builders, and AI-coding enthusiasts who want a 295B-parameter MoE model with 21B active parameters, 256K context, and strong reasoning + agent performance, on Apache-2.0 terms, with deployment paths via vLLM or SGLang and weights on H
Who should use it
Who should skip it
Skip Tencent-Hunyuan/Hy3 if the source link, documentation, or setup requirements do not align with your current workflow or stack.
About this signal
Tencent-Hunyuan/Hy3 is tracked by RepoRadar as a tencent 295b moe reasoning + age in the Model Release / Open-Weight LLM section. It was first seen on 2026-07-06 and last updated on 2026-07-06. The current verdict is 'try now' with a Gold tier and advanced setup difficulty. The standout signals for Tencent-Hunyuan/Hy3 are workflow potential (9.1) and momentum (9.0), while setup ease (4.2) trails — that balance shapes where it fits best. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned Tencent-Hunyuan/Hy3 a composite score of 8.0 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to evaluate an AI tool before you adopt it for the checklist behind this score.
Risk explanation
The 295B / BF16 weights need a 2x H100 / 1x H200 / 1x MI300X GPU budget at full precision -- a single H100 or a 4090 / 3090 / 5090 workstation is below the bar for full-precision inference; and the consumer MUST use the quantization recipe or the tensor-parallel path to fit the weights on a smaller GPU budget; the post-training pipeline was reworked across 50+ product teams; but the consumer MUST benchmark the model on the consumer's own workload (the README's productivity-scenario claims are for Tencent's own evaluation) before locking in production.