microllm-250m:latest
OLLAMA GGUFllama · 256.74M · F16
Jul 5, 2026 · Apple M4 Pro
huihui-devstral-small-2-24b-instruct-2512-abliterated-i1
LM-STUDIO GGUFmistral3 · 24B · Q4_K_S
Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
34 vs 78
Hardware Fit
100 vs 74
Quality Score
6 vs 79
Hardware
microllm-250m:latest huihui-devstral-sm…
MachineMac miniSystem manufacturer
CPUApple M4 ProAMD Ryzen 7 5800X 8-Core Processor
Cores1216
RAM24 GB32 GB
GPUApple M4 ProAMD Radeon RX 9060 XT
OSmacOS 26.5.2Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
microllm-250m:latest huihui-devstral-sm…
Tokens/sec291.617.5
First chunk50 ms20 ms
TTFT79 ms279 ms
Load time0.0 sN/A
Memory usage0.6 GB15.6 GB
Memory %2%49%
HW Fit Score Breakdown
microllm-250m:latest
Speed
50/50
TTFT
20/20
Memory
30/30
huihui-devstral-small-2…
Speed
29/50
TTFT
20/20
Memory
25/30
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
huihui-devstral-small-2…
Reasoning
16/20
Coding
17/20
Instruction
15/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest