Hunyuan A13B Instruct
Tencent · released Jun 25, 2025 · tencent/Hunyuan-A13B-Instruct
- Type
- Open weightsCustom licence
- Params
- 80.4B
- Context
- 131K
13B active per word · about 98K words of context · download allowed, licence restricts use
Our take
Written Sep 1, 2026Hunyuan A13B Instruct is a downloadable text model from Tencent that uses a mixture-of-experts design: 13 billion parameters are active per word out of 80.4 billion total. It handles up to 131,072 tokens in a single request, but no benchmark scores are available to measure its quality.
Pick this when you need a long context window with relatively low active-parameter compute, or when a custom licence is acceptable for your use case. Skip it if you need measured quality scores, a permissive licence, or verified throughput from multiple providers.
The case for it
- 131,072-token request limit with only 13 billion active parameters per word.
- Two hosted offers available for inference without self-hosting.
The case against it
- No measured quality or capability scores in our data — no chat, coding, reasoning or other task scores.
- Custom licence, not Apache 2.0 or MIT; terms are unspecified in our data.
- Throughput unverified on one of two tracked hosts.
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
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M2 Max (38-core GPU) · 96 GB
Room to spare. 18.3 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 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.14 in / $0.57 out
- Context served
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.14 / $0.57checked 4 hours ago | 131K | not measured | Unknown | Unknown | Unknown |
| SiliconFlowfp8Through OpenRouter | $0.14 / $0.57checked 4 hours ago | 131K118K max reply | 26 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 | ✗ | ✓ | ✓ |
| SiliconFlowfp8Through 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 allowsCustom licence, 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
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- tencent/Hunyuan-A13B-Instruct
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- tencent-hunyuan-a13b-instruct