mistral:latest
OLLAMA GGUFllama · 7.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
microllm-250m:latest
OLLAMA GGUFllama · 256.74M · F16
Jul 5, 2026 · Apple M4 Pro
Global Score
73 vs 34
Hardware Fit
100 vs 100
Quality Score
62 vs 6
Hardware
mistral:latest microllm-250m:latest
MachineMicro-Star International Co., Ltd. MS-7B79Mac mini
CPUAMD Ryzen 5 2600X Six-Core ProcessorApple M4 Pro
Cores1212
RAM16 GB24 GB
GPUNVIDIA GeForce GTX 1080Apple M4 Pro
OSMicrosoft Windows 11 Famille 10.0.26200macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced
Performance
mistral:latest microllm-250m:latest
Tokens/sec31.7291.6
First chunk102 ms50 ms
TTFT102 ms79 ms
Load time14.3 s0.0 s
Memory usage4.8 GB0.6 GB
Memory %30%2%
HW Fit Score Breakdown
mistral:latest
Speed
50/50
TTFT
20/20
Memory
30/30
microllm-250m:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
mistral:latest
Reasoning
8/20
Coding
13/20
Instruction
16/20
Structured
12/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
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
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