Back to leaderboard

microllm-250m:latest

OLLAMA GGUF

llama · 256.74M · F16

Not Rec.

Jul 5, 2026 · Apple M4 Pro

qwopus3.6-27b-coder-compat-mtp

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
34 vs 88
Hardware Fit
100 vs 80
Quality Score
6 vs 91

Hardware

microllm-250m:latest qwopus3.6-27b-code…
MachineMac miniASUS
CPUApple M4 ProAMD Ryzen 7 7800X3D 8-Core Processor
Cores1216
RAM24 GB31 GB
GPUApple M4 ProNVIDIA GeForce RTX 4090, Raphael
OSmacOS 26.5.2cachyos rolling
Archarm64x64
Power Modebalancedperformance

Performance

microllm-250m:latest qwopus3.6-27b-code…
Tokens/sec291.642.9
First chunk50 ms32 ms
TTFT79 ms413 ms
Load time0.0 sN/A
Memory usage0.6 GB24.6 GB
Memory %2%81%

HW Fit Score Breakdown

microllm-250m:latest

Speed
50/50
TTFT
20/20
Memory
30/30

qwopus3.6-27b-coder-com…

Speed
50/50
TTFT
20/20
Memory
10/30

Quality

microllm-250m:latest

Reasoning
1/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

qwopus3.6-27b-coder-com…

Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest