llamaperf

Kolibri-1 78B (3.46B active) A3.5B

on AMD Radeon 890M · llama.cpp · 262,000 ctx

Tone: mixedAMD hardware
Nov 20, 2026
Throughput
27.3 t/s gen · 430.0 tokens/s prompt processing (prefill)Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.
Quant
IQ2_M (GGUF)
System RAM
96 GB
VRAM reported
48 GB

Use cases

agenticcoding

Summary

User benchmarks Kolibri-1 78B at 27.28 t/s decode on a Minisforum AI X1 Pro with a Radeon 890M and 96GB RAM (48GB VRAM share). Setup is llama.cpp over Vulkan with IQ2_M at 262k context; prefill is 430 t/s and the model scored 5/7 on the user's gauntlet. User ranks it the fastest smart agent on the box, ahead of Qwen3.6-35B at 26.8-27.0 t/s and Qwen3-Next-80B at 26 t/s, and notes nothing bigger clears 10 t/s except small-active MoEs.