Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

gemma4:12b-mlx

OLLAMA GGUF
Excellent

Jul 4, 2026 · Apple M2 Pro

Global Score
70 vs 84
Hardware Fit
73 vs 82
Quality Score
68 vs 85

Hardware

llama3.1:8b-instru… gemma4:12b-mlx
Machine—MacBook Pro
CPUC1-ProApple M2 Pro
Cores010
RAM11 GB16 GB
GPUIntegrated / UnknownApple M2 Pro
OSunknown unknownmacOS 26.5
Archarm64arm64
Power Modeunknownbalanced

Performance

llama3.1:8b-instru… gemma4:12b-mlx
Tokens/sec6.527.2
First chunk950 ms732 ms
TTFT950 ms8.1 s
Load time11.5 s3.5 s
Memory usage4.4 GB7.1 GB
Memory %38%44%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

Speed
25/50
TTFT
20/20
Memory
28/30

gemma4:12b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

Quality

llama3.1:8b-instruct-q4…

Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

gemma4:12b-mlx

Reasoning
16/20
Coding
17/20
Instruction
13/20
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest