microllm-250m:latest
OLLAMA GGUFllama · 256.74M · F16
Jul 5, 2026 · Apple M4 Pro
qwen3.8-27b-claude-opus-reasoning-distilled
LM-STUDIO GGUFqwen35 · 27B · Q4_K_M
Aug 20, 2026 · Apple M4 Max
Global Score
34 vs 80
Hardware Fit
100 vs 63
Quality Score
6 vs 87
Hardware
microllm-250m:latest qwen3.8-27b-claude…
MachineMac miniMacBook Pro
CPUApple M4 ProApple M4 Max
Cores1216
RAM24 GB128 GB
GPUApple M4 ProApple M4 Max
OSmacOS 26.5.2macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced
Performance
microllm-250m:latest qwen3.8-27b-claude…
Tokens/sec291.624.0
First chunk50 ms20 ms
TTFT79 ms4.5 s
Load time0.0 sN/A
Memory usage0.6 GB15.7 GB
Memory %2%12%
HW Fit Score Breakdown
microllm-250m:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.8-27b-claude-opus…
Speed
27/50
TTFT
6/20
Memory
30/30
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
qwen3.8-27b-claude-opus…
Reasoning
19/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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