Hy-MT2-30B-A3B
Tencent · released May 11, 2026 · tencent/Hy-MT2-30B-A3B
- Type
- Open weightsApache License 2.0
- Params
- 30.1B
- Context
- 8K
3B active per word · about 6K words of context
Our take
Written Aug 20, 2026Hy-MT2-30B-A3B is a 30-billion-parameter text model from Tencent with downloadable weights and an 8,192-token request limit. It is a budget option with identical rates across its two hosts, though no quality scores are available to judge it against peers.
Pick this for budget text-only inference where consistent pricing across hosts matters, or for Tencent-hosted deployment if 55 tokens per second meets your latency needs. Skip it if you need measured quality data to compare alternatives, a wider context window, or verified throughput on every host you might use.
The case for it
- Open weights allow local or self-hosted deployment, though licence terms are undisclosed.
- Identical pricing on both tracked hosts removes provider-arbitrage friction.
The case against it
- No benchmark scores in our data, so there is no measured quality basis for choosing it over similarly-priced alternatives.
- 8,192-token request limit is narrow by current standards.
- Throughput unverified on OpenRouter; only the Tencent endpoint reports a figure.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Borderline fit on an estimated size. It leaves 1.9 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Comfortable fit
GeForce RTX 5090 · 32 GB
Room to spare. 9.9 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 3.1 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 2 hours ago — each listing carries its own date.
- per 1M tokens
- $0.074 in / $0.29 out
- Context served
- 8K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.074 / $0.29checked 2 hours ago | 8K | not measured | Unknown | Unknown | Unknown |
| Tencentfp8Through OpenRouter | $0.074 / $0.29checked 2 hours ago | 8K4K max reply | 54 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✗ | ✓ | ✓ |
| Tencentfp8Through OpenRouter | ✗ | ✓ | ✓ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- tencent/Hy-MT2-30B-A3B
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- tencent-hy-mt2-30b-a3b