Hy3
Tencenthuggingface.co/tencent/Hy3
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
Updated 22 min ago · first seen 11 Sept 2026
model_01M294WVW4C092JT6V607VWDPF
- Parameters
- 298.8B
- T2 · 3 h ago
- Context
- 256K tokens
- T2 · 1 h ago
- Released
- 2 Jul 2026
- T2 · 22 min ago
- License
- apache-2.0
- T2 · 2 h ago
Specification
- Release date
- 2 Jul 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 min agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- License
- apache-2.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Architecture
- HYV3ForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Parameters
- 298.8B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Context window
- 256K tokens
Source:Artificial AnalysisT2observed 1 h agomedium
- Max output
- 128K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Modalities
- text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Input modalities
- text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- File size
- 597.6 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Hugging Face repo
- tencent/Hy3
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Pipeline tag
- text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Downloads
- 12,590
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 min agomedium
- Likes
- 964
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Hf inference providers
- deepinfra
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Last modified
- 2026-07-20T07:01:39+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Aa median output tokens per second
- 81.8
Source:Artificial AnalysisT2observed 1 h agomedium
- Downloads all time
- 38,425
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 min agomedium
- Model type
- hy_v3
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Openrouter id
- tencent/hy3
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, max_completion_tokens, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Tags
- transformers, safetensors, hy_v3, text-generation, hunyuan, hy3, moe
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Weights dtype
- BF16, F32
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
31
Source tiers
T231
Freshest observation
22 min ago
Conflicts
None
Modalities
- Modalities
- text
- Input
- text
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 256K tokens
Source:Artificial AnalysisT2observed 1 h agomedium
- Max output
- 128K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| Artificial Analysis Intelligence Index | 25.77 | index | aa_slug=hy3 · version=4.3 · estimated=false | — | artificialanalysis.aiT2 |
| GPQA | 89.7% | accuracy | aa_slug=hy3 · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 33.46% | accuracy | aa_slug=hy3 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| SciCode | 48.61% | accuracy | aa_slug=hy3 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 0.51% | accuracy | aa_slug=hy3 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 64.42% | accuracy | aa_slug=hy3 · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| OpenRoutertencent/hy3 | $0.083 | $0.33 | $0.021 | — | 262.1K | 1 h ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- OpenRouter
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| NVIDIA DGX B200 | 4bit | 1,440 GB | 172.3 GB | Yes |
| Apple M3 Ultra | 4bit | — | 172.3 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 172.3 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 172.3 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 172.3 GB | Yes |
| Apple M2 Ultra | 4bit | — | 172.3 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 172.3 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 172.3 GB | No |
| NVIDIA H200 NVL | 4bit | 141 GB | 172.3 GB | No |
| Apple M1 Ultra | 4bit | — | 172.3 GB | No |
| Apple M3 Max | 4bit | — | 172.3 GB | No |
| Apple M4 Max | 4bit | — | 172.3 GB | No |
| Mac Studio (Apple M5 Max) | 4bit | — | 172.3 GB | No |
| MacBook Pro (Apple M5 Max) | 4bit | — | 172.3 GB | No |
| NVIDIA DGX Spark | 4bit | 128 GB | 172.3 GB | No |
| Apple M2 Max | 4bit | — | 172.3 GB | No |
| NVIDIA H100 NVL | 4bit | 94 GB | 172.3 GB | No |
| NVIDIA A100 80GB | 4bit | 80 GB | 172.3 GB | No |
| NVIDIA H100 SXM | 4bit | 80 GB | 172.3 GB | No |
| Apple M1 Max | 4bit | — | 172.3 GB | No |
| Apple M4 Pro | 4bit | — | 172.3 GB | No |
| Mac mini (Apple M5 Pro) | 4bit | — | 172.3 GB | No |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 172.3 GB | No |
| Apple M3 Pro | 4bit | — | 172.3 GB | No |
| Apple M1 Pro | 4bit | — | 172.3 GB | No |
| Apple M2 Pro | 4bit | — | 172.3 GB | No |
| Apple M4 | 4bit | — | 172.3 GB | No |
| iMac (Apple M4) | 4bit | — | 172.3 GB | No |
| Mac mini (Apple M6) | 4bit | — | 172.3 GB | No |
| MacBook Air (Apple M5) | 4bit | — | 172.3 GB | No |
| MacBook Pro (Apple M5) | 4bit | — | 172.3 GB | No |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 172.3 GB | No |
| Apple M2 | 4bit | — | 172.3 GB | No |
| Apple M3 | 4bit | — | 172.3 GB | No |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 172.3 GB | No |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 172.3 GB | No |
| Apple M1 | 4bit | — | 172.3 GB | No |
No lineage recorded
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Likes
Likesmetric.likes1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 964 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Hy3 scores 25.77 on Artificial Analysis Intelligence Index
artificial_analysisHy3: context length changed from 262144 to 256000
Context window262.1K tokens→256K tokensartificial_analysisHy3: release date changed from 2026-07-02 to 2026-07-06
Release date2 Jul 2026→6 Jul 2026openrouterHy3: release date changed from 2026-07-06 to 2026-07-02
Release date6 Jul 2026→2 Jul 2026huggingfaceOpenRouter lists Hy3 at $0.0825 in / $0.33 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/tencent/Hy3 | model_page | T2· Quality secondary | 22 min ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=tencent&p=0&sort=downloads | listing | T2· Quality secondary | 57 min ago | 3 |
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 1 h ago | 1 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 1 h ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/tencent/Hy3/raw/main/README.md | model_card | T2· Quality secondary | 1 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.