Params
26B-A4B
Fastest decode
173 tok/s
RTX 5090 32GB · Q4_K_M GGUF
Refusal
Abliterated
Setups
1
Best reported pair · not live serving speed ↗
Runs on
Quoted one-stream decode on real boxes.
No public weights link on this desk yet.
Google / community · MoE
Params
26B-A4B
Fastest decode
173 tok/s
RTX 5090 32GB · Q4_K_M GGUF
Refusal
Abliterated
Setups
1
Best reported pair · not live serving speed ↗
Quoted one-stream decode on real boxes.
No public weights link on this desk yet.