qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Mar 2, 2026 · Apple M4
lfm2.5:8b
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
73 vs 80
Hardware Fit
100 vs 95
Quality Score
62 vs 73
Hardware
qwen3:0.6b lfm2.5:8b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3:0.6b lfm2.5:8b
Tokens/sec145.298.5
First chunkN/A167 ms
TTFT1.4 s2.5 s
Load time0.7 s3.0 s
Memory usage4.1 GB6.0 GB
Memory %13%37%
HW Fit Score Breakdown
qwen3:0.6b
Speed
40/50
TTFT
30/20
Memory
30/30
lfm2.5:8b
Speed
50/50
TTFT
17/20
Memory
28/30
Quality
qwen3:0.6b
Reasoning
14/20
Coding
3/20
Instruction
11/20
Structured
13/15
Math
13/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
lfm2.5:8b
Reasoning
2/20
Coding
12/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Strong 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