Qwen3.5-122B-A10B
Qwen · released Feb 24, 2026 · Qwen/Qwen3.5-122B-A10B
- Type
- Open weightsApache License 2.0
- Params
- 125B
- Context
- 262K
10B active per word · about 197K words of context
Our take
Written Sep 30, 2026Qwen3.5-122B-A10B is a downloadable model you can run yourself, and its licence allows commercial use, changes and redistribution. Measured quality is mid-field, so treat it as a workhorse for everyday work rather than a leader.
Use it for everyday chat, retrieval and document work where the bill matters more than peak quality, or when you want to run the model on a single modern graphics card. Its licence allows commercial use, changes and redistribution (Apache License 2.0). Skip it if a task needs measured coding or reasoning evidence, or if you need a leader on chat preference.
The case for it
- About 10 billion of its 125.1 billion parameters work per token, so memory in use is closer to a small model than to a mid-size one — realistic on one modern graphics card.
- The licence allows commercial use, changes and redistribution (Apache License 2.0).
- Text, images and video go into the same request, so a screenshot or a clip does not have to be described in words first.
The case against it
- Chat preference is the only measured quality here: 81st of 168 on Arena Text (overall) as of 25 Sep 2026, a board that records which answer people preferred rather than whether it was correct.
- Nothing supplied measures coding or reasoning, so those tasks need a trial on work you can check yourself.
- Rates differ between the listed hosts, so the cheapest row is not automatically the one to pick.
How good is it?
EverydayGeneral questions and everyday reasoning
Arena Text (overall)81st of 168 · 1416
CodingWriting and fixing code on its own
Arena Coding85th of 168 · 1459
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing91st of 168 · 1366
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model7 scoresEvery figure we hold, from 7 boards, with who ran it and a link to the source — including the boards no rating above is built on.
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 M1 Ultra (64-core GPU) · 128 GB
Room to spare. 13.4 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 between 1 hour and 7 days ago — each listing carries its own date.
- per 1M tokens
- $0.26 in / $2.08 out
- Context served
- 262K
- Throughput
- ~65 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Alibaba CloudThrough OpenRouter | $0.26 / $2.08checked 1 hour ago | 262K66K max reply | 65 tok/s | No | Yesunknown period | Unknown |
| OpenRouterOpenRouter's own listing | $0.26 / $2.08checked 1 hour ago | 262K | not measured | Unknown | Unknown | Unknown |
| SiliconFlowfp8Through OpenRouter | $0.26 / $2.08checked 1 hour ago | 262K236K max reply | 40 tok/s | No | No | Confirmed |
| AtlasCloudfp8Through OpenRouter | $0.30 / $2.40checked 1 hour ago | 262K66K max reply | 26 tok/s | No | Yesunknown period | Unknown |
| DeepInfrafp4Direct | $0.29 / $2.40checked 7 days ago | 262K | not measured | Unknown | Unknown | Unknown |
| Novita AIbf16Direct and through OpenRouter | $0.40 / $3.20checked 1 hour ago | 262K66K max reply through OpenRouter | 40 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
OpenRouter
DeepInfra
Novita AIAcross the 6 listings we hold: 4 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 2 do not say. 2 appear in the zero-retention registry we check (1 of them only through OpenRouter); 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 |
|---|---|---|---|
| Alibaba CloudThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| SiliconFlowfp8Through OpenRouter | ✗ | ✓ | ✓ |
| AtlasCloudfp8Through OpenRouter | ✓ | ✓ | ✓ |
| DeepInfrafp4Direct | |||
| Novita AIbf16Direct and through OpenRouter | ✓ | ✓ | ✗ |
Tool calling: 4 of 6 listings say yes, 1 says no, 1 publishes no parameter list. JSON output: 5 of 6 listings say yes, 1 publishes no parameter list. Strict schema: 4 of 6 listings say yes, 1 says no, 1 publishes no parameter list.
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.
- 1 of 6 listings publishes no parameter list, so what its API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 6 listings do not say whether they train on prompts, and 1 answers only through OpenRouter, not for its own listing.
- 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
- Qwen/Qwen3.5-122B-A10B
- Architecture
- Mixture of experts
- Takes in, gives back
- Text, images and video in, text out
- Catalogue slug
- qwen-qwen3-5-122b-a10b