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 Aug 2, 2026Hunyuan A13B Instruct is a downloadable text model from Tencent that uses a mixture-of-experts design, keeping 13 billion parameters active out of 80.4 billion total. It offers a 131,072-token request limit and is positioned as a mid-tier efficient option, though no independent quality scores are available yet.
Pick this when you need a large request limit at mid-market pricing, or for throughput-sensitive batch work where the active-parameter design may help. Consider it for Tencent ecosystem integration or Chinese-language text tasks, though benchmark evidence for either is unverified. Skip it if you need a permissive licence for redistribution, measured quality scores before deployment, or price competition between multiple hosts.
The case for it
- 131,072-token request limit at its price tier — no cheaper 128K-plus option in this model's own data.
- 13 billion active parameters per token from 80.4 billion total, a substantial active count for an efficient architecture.
The case against it
- No measured quality scores in our data — chat, reasoning, coding and general knowledge benchmarks are all unverified.
- Custom restricted licence, not Apache 2.0 or MIT, with terms that limit commercial use and redistribution.
- Only two tracked hosts with identical pricing and thin throughput data, so there is no price competition to exploit.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Hunyuan A13B Instruct — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 2 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- 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 |
|---|---|---|---|---|---|---|
| OpenRouter | $0.14 / $0.57 | 131K | not measured | Unknown | Unknown | Unknown |
| SiliconFlowfp8 | $0.14 / $0.57 | 131K | 62 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✓ | ✓ |
| SiliconFlowfp8 | ✗ | ✓ | ✓ |
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
Dates behind this page
Prices last checked 35h ago
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 board we watch has turned up a score, 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 do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
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
- Modality record
- text->text
- Catalogue slug
- tencent-hunyuan-a13b-instruct