- Source
- Model registry API
- Verified
- 19 Sep 2026
- Confidence
- High
01What this is
- Author
- Qwen
- Family
- Qwen3 Coder
- Task
- text-generation
- Hugging Face
- Qwen/Qwen3-Coder-Next
- OpenRouter
- qwen/qwen3-coder-next
- Also known as
- Qwen3 Coder Next, qwen3-coder-next, qwen coder
02Registry facts
- LicenceFACT
apache-2.0
- FreshRetrieved 19 Sep 2026
- ParametersFACT
79.7B
- FreshRetrieved 19 Sep 2026
- Context lengthFACT
not returned by the registry
- Evidence not verified
- Downloads (30 days)FACT
521,406
- FreshRetrieved 19 Sep 2026
- LikesFACT
1,646
- FreshRetrieved 19 Sep 2026
- GatedFACT
no
- FreshRetrieved 19 Sep 2026
Model
- downloadsFACT
521406
- Verification may be outdatedRetrieved 19 Sep 2026
- gatedFACT
false
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · NovitaFACT
262144
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · StreamLakeFACT
256000
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · ParasailFACT
262144
- Verification may be outdatedRetrieved 19 Sep 2026
- likesFACT
1646
- Verification may be outdatedRetrieved 19 Sep 2026
- model licenseFACT
apache-2.0
- Verification may be outdatedRetrieved 19 Sep 2026
- parameter countFACT
79674391296
- Verification may be outdatedRetrieved 19 Sep 2026
Pricing
- hosted price completion per m · NovitaFACT
1.5000
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · StreamLakeFACT
0.9000
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · ParasailFACT
0.8000
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · NovitaFACT
0.2000
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · StreamLakeFACT
0.1800
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · ParasailFACT
0.1200
- AgeingRetrieved 19 Sep 2026
Other
- available on platform · alibabaFACT
alibaba
Evidence not verified — the quoted phrase was not found in the fetched document.
- Evidence not verified
- available on platform · awsFACT
aws
The source document changed after this was recorded; it is queued for re-checking.
- Verification may be outdatedRetrieved 19 Sep 2026
- last modifiedFACT
2026-02-03T16:16:38.000Z
- Verification may be outdatedRetrieved 19 Sep 2026
- libraryFACT
transformers
- AgeingRetrieved 19 Sep 2026
03VRAM by quantisation
Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: 79.7B parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).
| Quantisation | Weights | Total |
|---|---|---|
| bf16bf16 is two bytes per weight, the same arithmetic as fp16. | 159.35 GB | 195.6 GB |
| fp8 | 79.67 GB | 103.97 GB |
| int4 | 39.84 GB | 58.16 GB |
What this estimate assumes
- Weights: 79.7B parameters × 2 bytes per parameter (fp16) = 159.35 GB.
- No model configuration was supplied, so the KV cache uses the size heuristic for this band: 0.328 MB per token, from Qwen2.5-72B-Instruct (80 × 8 × 128).
- KV cache: 0.328 MB per token × 8,192 tokens of context × 4 concurrent requests = 10.74 GB, sized for every user holding a full context at once.
- Overhead: 15% of weights plus KV cache for the runtime, activations and memory fragmentation = 25.51 GB.
- GB means 10⁹ bytes, matching how GPU memory is advertised.
- KV cache held at fp16 (2 bytes per element); quantising weights does not by itself quantise the cache.
- Peak figure, not average: prefix caching and paged attention usually keep real usage lower, while speculative decoding, CUDA graphs and a second resident model push it higher.
- "Concurrent" counts requests generated at the same instant, not people: 4 simultaneous requests is the worst case this estimate is built on — measure yours before buying.
04Hardware profiles
No hardware profile was sized for this answer.
05Hosted providers
- Prompt (per million tokens, USD)FACT
0.12
Source: openrouter
- FreshRetrieved 19 Sep 2026
- Completion (per million tokens, USD)FACT
0.7999999999999999
- FreshRetrieved 19 Sep 2026
| Provider | Context |
|---|---|
| Parasail | 262,144 |
| StreamLake | 256,000 |
| Novita | 262,144 |
| Alibaba | 262,144 |
06Deployment stacks
No published deployment stack names this model yet.
07Evidence
- 01Tier 2official vendor legal documentationVendor legal and technical documentation
Models at a glance - Amazon Bedrock
https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards.html
AgeingRetrieved 19 Sep 2026sha256:4c3b2b5762261 record
- 02–10Tier 4official repository / model cardOpenRouter
OpenRouter endpoints — qwen/qwen3-coder-next
https://openrouter.ai/api/v1/models/qwen/qwen3-coder-next/endpoints
AgeingRetrieved 19 Sep 2026sha256:6fac9ef4b0b29 records · · · · · · · ·
- 11–17Tier 4official repository / model cardHugging Face Hub
Hugging Face model card data — Qwen/Qwen3-Coder-Next
https://huggingface.co/api/models/Qwen/Qwen3-Coder-Next
Verification may be outdatedRetrieved 19 Sep 2026sha256:d2d838ff708e7 records · · · · · ·
Improve this page
Sign in to contribute
From the field
0 deployments · 0 questions
Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.