Loading...
Loading...
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion. This model is optimized for instruction-following without “thinking mode”, and integrates well with OpenAI-compatible tool-use formats.
Quality Index
20.0
187th of 444
Top 43%
Coding Index
19.4
153rd of 354
Top 43%
Math Index
29.0
187th of 268
Top 70%
Price/1M
$0.90
478th cheapest
200% above median
Top 71%
Speed
25 tok/s
Top 60%
TTFT
1.45s
Context Window
160K
144th largest
Top 41%
Input
$0.45
per 1M tokens
Output
$2.25
per 1M tokens
Blended
$0.90
per 1M tokens
Cheaper than 29% of models. Median price is $0.30/1M tokens.
Daily
$0.90
Monthly
$27.00
25
tokens/sec
Faster than 40% of models
1.45
seconds
Faster than 20% of models
1.45
seconds
Faster than 32% of models
Market Median
45 tok/s
44% slower
Median TTFT
0.42s
246% slower
Throughput/Dollar
28
tok/s per $/1M
Speed Comparison
Context Window
160K
tokens
Larger than 59% of models
Max Output
33K
tokens
20% of context
1.1M
982
24-48 GB
A6000 / M3 Ultra