Qwen3.6 27B
Qwen · released Apr 21, 2026 · Qwen/Qwen3.6-27B
- Type
- Open weightsApache License 2.0
- Params
- 27.8B
- Context
- 262K
about 197K words of context
Our take
The case for it
- 27 billion parameters: a standard compressed size fits in 24GB-class GPUs, unlike the 400-billion-plus open mixture-of-experts models.
- Text, image and video input in a mid-size model.
The case against it
- Output price is relatively high for its size class.
How good is it?
EverydayGeneral questions and everyday reasoning
Not yet scored on Arena Text (overall). It is on LiveBench Data Analysis, in 43rd of 58 with 70.43.
CodingWriting and fixing code on its own
Not yet scored on Arena Coding. It is on LiveBench Coding, in 47th of 58 with 71.79.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on LiveBench Agentic Coding, in 55th of 58 with 39.29.
WritingDrafting and rewriting prose
Not yet scored on Arena Creative Writing. It is on LiveBench Language, in 57th of 58 with 63.3.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model8 scoresEvery figure we hold, from 8 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?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 3 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 11 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. 4.2 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 2 hours and 8 hours ago — each listing carries its own date.
Phala, through OpenRouter
Cheapest of the 4 listings we can compare like for like — at 262K of context, out of 8 in the table below. One cheaper row there is outside that comparison: a different quantisation.
- per 1M tokens
- $0.32 in / $2.70 out
- Context served
- 262K
- Throughput
- ~109 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Chutesfp8Through OpenRouter | $0.30 / $2.00checked 8 hours ago | 262K66K max reply | 8 tok/s | No | Yesunknown period | Unknown |
| PhalaThrough OpenRouter | $0.32 / $2.70checked 2 hours ago | 262K262K max reply | 109 tok/s | No | No | Confirmed |
| Alibaba CloudThrough OpenRouter | $0.45 / $2.70checked 2 hours ago | 262K66K max reply | 38 tok/s | No | Yesunknown period | Unknown |
| OpenRouterOpenRouter's own listing | $0.32 / $3.20checked 2 hours ago | 262K | not measured | Unknown | Unknown | Unknown |
| SiliconFlowfp8Through OpenRouter | $0.30 / $3.20checked 2 hours ago | 262K236K max reply | 20 tok/s | No | No | Confirmed |
| DeepInfrafp8Direct and through OpenRouter | $0.32 / $3.20checked 2 hours ago | 262K82K max reply through OpenRouter | 41 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Venice AIfp8Through OpenRouter | $0.33 / $3.25checked 2 hours ago | 256K66K max reply | 50 tok/s | No | No | Confirmed |
| Novita AIDirect | $0.60 / $3.60checked 2 hours ago | 262K | not measured | Unknown | Unknown | Unknown |
OpenRouter
DeepInfra
Novita AIAcross the 8 listings we hold: 6 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 2 do not say. 4 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 |
|---|---|---|---|
| Chutesfp8Through OpenRouter | ✓ | ✗ | ✓ |
| PhalaThrough OpenRouter | ✓ | ✓ | ✓ |
| Alibaba CloudThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| SiliconFlowfp8Through OpenRouter | ✓ | ✓ | ✓ |
| DeepInfrafp8Direct and through OpenRouter | ✓ | ✓ | ✓ |
| Venice AIfp8Through OpenRouter | ✓ | ✓ | ✓ |
| Novita AIDirect |
Tool calling: 7 of 8 listings say yes, 1 publishes no parameter list. JSON output: 6 of 8 listings say yes, 1 says no, 1 publishes no parameter list. Strict schema: 7 of 8 listings say yes, 1 publishes no parameter list.
Models people weigh against Qwen3.6 27B
When we formed this view
Recent changes
What moved
cache read −80% ($0.150 → $0.030 per 1M tokens)What moved
input +15% ($0.27 → $0.31 per 1M tokens), output +16% ($1.89 → $2.19 per 1M tokens), cache read +46% ($0.13 → $0.19 per 1M tokens)What moved
cache read −80% ($0.150 → $0.030 per 1M tokens)What moved
input −4% ($0.28 → $0.27 per 1M tokens), output −5% ($1.99 → $1.89 per 1M tokens), cache read −7% ($0.14 → $0.13 per 1M tokens)What moved
input $0.3078 → $0.28, output $2.592 → $1.99 per 1M tokensWhat 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 8 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 8 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/Qwen3.6-27B
- Architecture
- Dense
- Takes in, gives back
- Text, images and video in, text out
- Catalogue slug
- qwen-qwen3-6-27b