Loading...
Loading...
Quality Index
14.3
282nd of 440
Top 64%
Coding Index
7.3
292nd of 350
Top 83%
Math Index
27.3
189th of 268
Top 71%
Price/1M
$0.31
339th cheapest
At median
Top 50%
Speed
136 tok/s
Top 17%
TTFT
1.01s
Context Window
131K
145th largest
Top 63%
Input
$0.18
per 1M tokens
Output
$0.70
per 1M tokens
Blended
$0.31
per 1M tokens
Cheaper than 50% of models. Median price is $0.31/1M tokens.
Daily
$0.31
Monthly
$9.30
136
tokens/sec
Faster than 83% of models
1.01
seconds
Faster than 29% of models
Market Median
46 tok/s
197% faster
Median TTFT
0.43s
136% slower
Throughput/Dollar
439
tok/s per $/1M
Speed Comparison
Context Window
131K
tokens
Larger than 37% of models
Max Output
33K
tokens
25% of context
8.9M
Downloads (30d)
824
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.