Tencent Hy3: 295B Open-Source MoE Model for Agentic Coding — Apache 2.0, Free API, 256K Context

On July 6, 2026, Tencent Hunyuan posted a launch thread that crossed 219K views within hours:

"🚀 Hy3 is here. 295B MoE. Best in its size class. Rivals trillion-scale flagships. Reliable and affordable for most agentic use cases. Apache 2.0. Friendly for commercial use. FREE API for 2 weeks."

Update — July 14, 2026: Tencent released 1-bit & 4-bit GGUF quants for llama.cpp + MTP on 128 GB single-GPU rigs — no 8× H20 cluster required for local inference.

The links pointed to three surfaces developers actually use: Hugging Face weights, the official research page, and a free OpenRouter route. Within hours, Nous Research and Kilo Code announced complimentary Hy3 access in their portals — signaling this is not a paper release but a production agent model aimed at the same market as GLM-5.2 and DeepSeek's pricing floor.

Hy3 lands squarely in explainx.ai's China AI playbook thesis: ship capable open weights, undercut closed APIs on cost, and let enterprises route agent workloads through commodity inference.

TL;DR — Hy3 at a glance

Why Hy3 matters in July 2026

Three structural shifts make this release bigger than another benchmark slide:

1. Agent reliability is the product — Hy3's post-training focused on tool-call stability, output-format constraints, and scaffolding variance (SWE-bench accuracy within 4% across CodeBuddy, Cline, and KiloCode setups per Tencent).
2. Open weights + free API window — matches the free-models playbook: let developers habituate on zero marginal cost, then compete on hosted inference price.
3. Apache 2.0 at 295B scale — enterprises that cannot touch US export-controlled APIs get a permissive license alternative for non-regulated coding agents.

Nous Research framed the positioning clearly: "focused on cost-effective agentic use, and particularly strong on coding, tool-calling reliability, reasoning, and 256K long-context tasks."

Architecture — efficient MoE, not a dense giant

Hy3 is a sparse MoE, not a 295B dense transformer you pay for on every token.

explainx.ai read: total parameter count is a marketing headline; 21B active is what shapes latency and per-token cost. That is why Tencent claims Hy3 "rivals trillion-scale flagships" — sparse activation lets a ~300B model punch like a much larger dense stack on agent benchmarks, without activating every weight.

For MoE context at even larger scale, compare NVIDIA Nemotron 3 Ultra (550B) — another open-weight agent-first design from June 2026.

What improved since Hy3 Preview (April 2026)

Tencent shipped Hy3 Preview in late April 2026, then ran a product feedback loop before the July 6 GA release.

Post-training scale-up

• Feedback from 50+ internal Tencent products
• Higher-quality SFT data and expanded RL training
• Blind human eval: 270 experts, real work tasks, Hy3 scored 2.67/4 vs GLM-5.1 at 2.51/4

Production fixes (not just benchmark chasing)

Tencent's stated principle for knowledge tasks: "answer when grounded, state when evidence is missing, do not conflate sources or fabricate data."

That matters for agents — a model that hallucinates file paths or API shapes breaks CI faster than one that scores lower on trivia QA.

Benchmarks — public leaderboards and reported agent scores

Hugging Face evaluation results (official)

Reported in launch coverage (verify on your scaffold)

Grok's X summary and early reposts cited SWE-Bench Multilingual at 75.8% and Terminal Bench at 71.7%, with comparisons to GLM-5.2 and GPT-5.5-class models. Those numbers did not appear on the Hugging Face card at publish time — treat them as directional launch claims, not substitutes for your own eval harness.

Practical rule: if you run agents in Kilo, Cline, or Claude Code-style loops, benchmark your repo, your tools, your failure modes — not a single SWE-bench row.

Agentic strengths — where Hy3 is aiming

Tencent highlights five productivity lanes:

• Coding — SWE-bench leadership tier for open weights
• Office / financial modeling — long-context document workflows
• Frontend design — strongest blind-eval gains vs GLM-5.1
• Game development — multi-file coherence
• CI/CD and data/storage — operational tasks in the 270-expert eval

Tool-call reliability is the recurring theme. Hy3 ships dedicated parsers for vLLM (--tool-call-parser hy_v3) and SGLang (hunyuan), plus reasoning_effort modes (no_think, low, high) for chain-of-thought control.

Kilo Code's launch demo — one-shot "Create a 3D HTML visualizer of Earth spinning in space" across Opus, Fable, and Hy3 — is anecdotal, but it matches the frontend strength Tencent claims in blind evals.

Free access — where to try Hy3 this week

For agent developers already comparing Claude Code vs Codex vs GLM-5.2 plans, the OpenRouter free window is the lowest-friction A/B test: same prompt, same tools, swap model route.

Self-hosting — hardware reality check

Tencent's deployment guide is explicit:

"Hy3 has 295B parameters in total. To serve it on 8 GPUs, we recommend using H20-3e or other GPUs with larger memory capacity."

vLLM example (8-way tensor parallel + MTP):

export VLLM_FLASHINFER_ALLREDUCE_BACKEND=trtllm
vllm serve tencent/Hy3 \
  --tensor-parallel-size 8 \
  --speculative-config.method mtp \
  --speculative-config.num_speculative_tokens 2 \
  --tool-call-parser hy_v3 \
  --reasoning-parser hy_v3 \
  --enable-auto-tool-choice \
  --port 8000 \
  --served-model-name hy3

SGLang ships an equivalent recipe with EAGLE speculative decoding.

The "Goldilocks for 96–256 GB VRAM" reply — nuance

One viral reply called Hy3 "just the right size for the 96~256 VRAM crowd." That is misleading for full-weight serving. At 299B parameters in BF16, you need datacenter multi-GPU clusters, not a single RTX 5090 or Mac Studio.

Where the reply has a point: 21B active parameters means each inference step is closer to a large dense model than a 300B dense monster — so per-token cost on hosted APIs can feel "Goldilocks" even when weight storage is not.

Hy3 vs GLM-5.2 — the comparison everyone is making

Neither replaces the other automatically. GLM-5.2 has deeper explainx.ai coverage as China's response to the Fable export ban. Hy3 is Tencent's bid for default agent backbone inside Chinese big-tech product stacks — then exported globally via OpenRouter.

If you need a security-benchmark lens, see Zhipu vs Claude Mythos on bug finding. Hy3's launch emphasized shipping velocity and tool stability, not CVE discovery leaderboards.

Quickstart — OpenAI-compatible API after vLLM boot

from openai import OpenAI

client = OpenAI(base_url="http://127.0.0.1:8000/v1", api_key="EMPTY")

response = client.chat.completions.create(
    model="hy3",
    messages=[
        {"role": "user", "content": "Refactor this FastAPI route to async."},
    ],
    temperature=0.9,
    top_p=1.0,
    extra_body={"chat_template_kwargs": {"reasoning_effort": "high"}},
)
print(response.choices[0].message.content)

Tencent recommends temperature=0.9, top_p=1.0. Use reasoning_effort: "high" for math, coding, and multi-step agents; "no_think" for direct responses.

Enterprise and compliance notes

Apache 2.0 removes license friction for commercial agents — but not data-sovereignty or export-control questions.

• Regulated workloads (PII, HIPAA, defense) still need jurisdiction review before routing to Chinese-origin models — same framing as Asian AI alternatives post-Mythos ban.
• Model-agnostic gateways (OpenRouter, LiteLLM) let you tier routes: US closed APIs for sensitive data, Hy3/GLM/DeepSeek for cost-sensitive coding sandboxes.
• Tencent also ships AngelSlim quantization and a finetuning guide for teams that need domain adapters without full pretraining.

Who should switch, who should wait

Try Hy3 now if:

• You run agent scaffolds (Kilo, Cline, custom MCP loops) and want a free two-week bake-off
• You need 256K context for repo-scale or document-heavy agents
• You want Apache 2.0 weights for on-prem experimentation (with 8-GPU budget)

Wait if:

• You only have consumer GPUs under 128 GB — use GGUF guide VRAM table or API hosts instead of self-hosting full quants
• Your eval is security-critical and you have not red-teamed the model on your stack
• You are standardized on GLM Coding Plan economics and off-peak multipliers already work for you

Related on explainx.ai

• Hy3 GGUF 1-bit/4-bit — single-GPU llama.cpp + MTP (Jul 14)
• China's AI playbook — free models, cheap compute
• GLM-5.2 launches as Fable export-ban response
• GLM-5.2 MIT open source — Code Arena #2 (July 2026)
• GLM-5.2 vs Fable 5 on planning benchmarks
• Claude Code vs Codex vs Gemini CLI vs GLM-5.2 pricing
• DeepSeek V4 Pro disrupts AI pricing
• Zhipu matches Claude Mythos on security benchmarks
• NVIDIA Nemotron 3 Ultra — 550B open MoE
• Tencent Hunyuan HY-World 2.0 — 3D world models
• Loop engineering for coding agents

Official sources: Hugging Face — tencent/Hy3 · Tencent Hy research · OpenRouter free route · Tencent Hunyuan on X

Specs, free-API windows, and benchmark scores reflect Tencent's July 6, 2026 release and Hugging Face leaderboard entries as of July 7, 2026. Free API promotions expire — confirm current pricing on OpenRouter before production routing. Self-hosting requirements may change as quantization recipes mature.