Loading...
Loading...
Quality Index
32.4
87th of 440
Top 20%
Coding Index
25.3
107th of 350
Top 31%
Price/1M
$0.11
239th cheapest
64% below median
Top 35%
Speed
60 tok/s
Top 41%
TTFT
0.41s
Context Window
256K
91st largest
Top 29%
Input
$0.10
per 1M tokens
Output
$0.15
per 1M tokens
Blended
$0.11
per 1M tokens
Cheaper than 65% of models. Median price is $0.31/1M tokens.
Daily
$0.11
Monthly
$3.39
60
tokens/sec
Faster than 59% of models
0.41
seconds
Faster than 53% of models
Market Median
46 tok/s
31% faster
Median TTFT
0.43s
5% faster
Throughput/Dollar
533
tok/s per $/1M
Speed Comparison
Context Window
256K
tokens
Larger than 71% of models
2.8M
Downloads (30d)
958
Likes
apache-2.0
Permissive license allowing commercial use, modification, and distribution.
Hardware Requirements
Quantization Available
Check HuggingFace for GGUF, GPTQ, and AWQ quantized versions that require significantly less VRAM.