Qwen 3 Coder Next FP8
Qwen develops the Qwen 3 Coder Next, a chat-based model excelling at code completion, generation, and review, as well as function calling and text generation. Its advanced agentic capabilities enable robust performance in dynamic coding tasks, leveraging long-horizon reasoning and complex tool usage.
Input
Output
Context
262K
Max Output
66K
Parameters
79.7B
Technical Specifications
Model TypeChat
Context Window262,144 tokens
Max Output Tokens65,536 tokens
Parameters79.7B
Release DateFeb 1, 2026
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
9.3%
HLE
40.0%
AA-LCR
73.7%
GPQA
79.5%
Tau2-Bench
35.2%
IFBench
32.3%
SciCode
5.2%
Tau2 Banking
36.2
Coding
21.1
Intelligence
18.2%
Terminal-Bench Hard
38.2%
Terminal-Bench 2.1
133
Speed (tok/s)
0.893
TTFA (s)
0.893
TTFT (s)
Resources & Links
Estimated GPU Requirements for Qwen 3 Coder Next FP8
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by Qwen
qwen3-235b-a22b-thinking-2507262K context · 235B · Open weightsQwen 3 4B Thinking 2507262K context · 4B · Open weightsQwen 2.5 32B Instruct33K context · 32.8B · Open weightsQwen 2.5 14B Instruct AWQ33K context · 14.8B · Open weightsQwen 3 VL 8B Instruct262K context · 8.8B · Open weightsQwen 3.5 9B262K context · 9.7B · Open weights
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 6, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.