Qwen3 Coder Next
Qwen · released Jan 30, 2026 · Qwen/Qwen3-Coder-Next
- Type
- Open weightsApache License 2.0
- Params
- 79.7B
- Context
- 262K
about 197K words of context
Our take
Written Aug 3, 2026Qwen3 Coder Next is a large downloadable code-specialist model with a permissive Apache licence and a 262,144-token request limit. It is built for developers who need to work with large codebases, though no benchmark scores have been published yet.
Pick this when you need a permissive licence for commercial code tasks, or when you are working with large repositories that need a very long request limit. Use it if you want to shop around for price, since the cheapest tracked host undercuts the provider's own API by a wide margin. Skip it if you need measured quality data to make a decision, or if you need guaranteed throughput at the lowest price point.
The case for it
- Apache 2.0 licence allows commercial use, fine-tuning and redistribution with no restrictions.
- 262,144-token request limit fits large codebases and long files.
- The cheapest tracked host is well below the provider's own API on both input and output rates.
The case against it
- No benchmark scores in the catalogue — no coding, reasoning or chat quality has been verified.
- Throughput varies by more than half across hosts at similar price points, so the cheapest option may not be the fastest.
- At 79.7 billion dense parameters, local self-hosting likely needs datacentre-class hardware.
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 Qwen3 Coder Next — 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. 18.8 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 7 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
- $0.12 in / $0.80 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Parasailbf16 | $0.12 / $0.80 | 262K | 39 tok/s | No | No | Confirmed |
| Ionstreamfp8 | $0.11 / $0.80 | 262K | 65 tok/s | No | No | Confirmed |
| OpenRouter | $0.12 / $0.80 | 262K | not measured | Unknown | Unknown | Unknown |
| StreamLake | $0.18 / $0.90 | 256K | 30 tok/s | No | Yesunknown period | Unknown |
| Alibaba Cloud | $0.30 / $1.50 | 262K | 34 tok/s | No | Yesunknown period | Unknown |
| Novita AI | $0.20 / $1.50 | 262K | not measured | Unknown | Unknown | Unknown |
| Novita AIfp8 | $0.20 / $1.50 | 262K | 19 tok/s | No | No | Confirmed |
Novita AIAcross the 7 listings we hold: 5 say they do not train on prompts, 0 say they do and 2 do not say. 3 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 |
|---|---|---|---|
| Parasailbf16 | ✓ | ✓ | ✓ |
| Ionstreamfp8 | ✓ | ✓ | ✓ |
| OpenRouter | ✓ | ✓ | ✓ |
| StreamLake | ✓ | ✓ | ✗ |
| Alibaba Cloud | ✓ | ✓ | ✗ |
| Novita AI | |||
| Novita AIfp8 | ✓ | ✓ | ✗ |
Tool calling: 6 of 7 listings say yes, 1 publishes no parameter list. JSON output: 6 of 7 listings say yes, 1 publishes no parameter list. Strict schema: 3 of 7 listings say yes, 3 say no, 1 publishes no parameter list.
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.
- 1 of 7 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 7 listings do not say whether they train on prompts.
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-Coder-Next
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- qwen-qwen3-coder-next