Comment by eurekin
9 hours ago
> ~1000 bytes per context token per user
Where's that figure comning from? Last time I checked (could be the 3.6 Qwen 27b) single token needed 32kb
9 hours ago
> ~1000 bytes per context token per user
Where's that figure comning from? Last time I checked (could be the 3.6 Qwen 27b) single token needed 32kb
The smallest I have seen is DeepSeek 4.1 flash at 890 bytes per token.