BREAKING
Qwythos-9B Adds 1M-Token Context
0
tok
context length
0
B
parameters
0
M
CoT tokens trained
MMLU Jumps to 0.575
base Qwen3.5
0.232
Qwythos
0.575
0
pt
GSM8K strict gain
0
/7
agent tasks passed
0
k
GGUF likes
Strengths vs Trade-offs
Strengths
●
Apache 2.0 open weights
●
Native tool calling
●
Strong local coding
Trade-offs
●
Heavy VRAM at full 1M
●
256k-512k realistic on H100
●
Slight short-input quality dip
Small Open Weights Close the Gap
AI NEWS BLITZ
Empero AI has released an open 9B model that handles roughly one million tokens of context.