Back to leaderboard

aya:8b

OLLAMA GGUF

command-r · 8.0B · F16

Good

Mar 1, 2026 · Apple M4

lfm2.5:8b

OLLAMA GGUF

lfm2moe · 8.5B · Q4_K_M

Excellent

Aug 24, 2026 · Apple M1 Pro

Global Score
66 vs 80
Hardware Fit
92 vs 95
Quality Score
55 vs 73

Hardware

aya:8b 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

aya:8b lfm2.5:8b
Tokens/sec20.098.5
First chunkN/A167 ms
TTFT300 ms2.5 s
Load time0.9 s3.0 s
Memory usage6.0 GB6.0 GB
Memory %19%37%

HW Fit Score Breakdown

aya:8b

Speed
32/50
TTFT
30/20
Memory
30/30

lfm2.5:8b

Speed
50/50
TTFT
17/20
Memory
28/30

Quality

aya:8b

Reasoning
10/20
Coding
6/20
Instruction
13/20
Structured
15/15
Math
2/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor 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
View aya:8b details | View lfm2.5:8b details

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