Qwen3.8 125B (6B active) Flash-Next

on AMD Radeon AI PRO R9700 32GB · llama.cpp

Sep 7, 2026

Throughput

26.6 t/s gen · 279.3 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

Q4_K_XL (GGUF)

VRAM reported

32 GB

Summary

User reports tensor-read-lazy with mmap fitting a Q4 model on a system with an AMD Radeon AI PRO R9700, RX 9070 XT, and Radeon 8060S (Strix Halo). The model is 103.68 GiB with 176.94 B params. Prompt processing reaches 279.25 t/s and generation 26.63 t/s.

View source ↗