llamaperf

Agents-A1 35B (3B active) Uncensored-MTP-APEX

on NVIDIA RTX 5070 Ti · llama.cpp

Tone: positiveNVIDIA hardware
Sep 9, 2026
Throughput
97.0 t/s gen
Quant
APEX Compact (GGUF)
System RAM
64 GB

Summary

User reports a 35B MoE agentic model that beats Qwen3.6 and DeepSeek V4 Pro in some scenarios. The model is available in the SC117/Agents-A1-Uncensored-MTP-APEX-GGUF repository. A 4B dense variant is also mentioned but is not attractive.