Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Excellent

Jul 4, 2026 · Apple M2 Pro

Global Score
80 vs 89
Hardware Fit
52 vs 88
Quality Score
92 vs 89

Hardware

qwen/qwen3.8-27b gemma4:12b
MachineMacBook ProMacBook Pro
CPUApple M4 MaxApple M2 Pro
Cores1610
RAM128 GB16 GB
GPUApple M4 MaxApple M2 Pro
OSmacOS 26.5.2macOS 26.5
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.8-27b gemma4:12b
Tokens/sec16.118.5
First chunk14 ms752 ms
TTFT5.8 s752 ms
Load time8.5 s6.1 s
Memory usage0.0 GB7.5 GB
Memory %0%47%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
17/50
TTFT
5/20
Memory
30/30

gemma4:12b

Speed
42/50
TTFT
20/20
Memory
26/30

Quality

qwen/qwen3.8-27b

Reasoning
19/20
Coding
16/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

gemma4:12b

Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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