llamaperf

Qwen2.5-Coder 1.5B FFCraft

on RX 6400 · llama.cpp

Tone: positive
Nov 20, 2026
Throughput
57.0 t/s gen
Quant
Q8_0 (GGUF)
VRAM reported
4 GB

Use cases

coding

Summary

User reports FFCraft-1.5B, a fine-tune of Qwen2.5-Coder-1.5B, running at about 57 tok/s on an AMD RX 6400 via Vulkan. Setup is llama.cpp with a Q8_0 GGUF (1.6GB) and no system prompt; the model was trained with full bf16 LoRA on an L4. On 60 held-out FFmpeg tasks the fine-tune passed 95.0% with zero system prompt versus 28.3% for the base model; the user notes exotic multi-input filter_complex pipelines remain outside its training distribution.