gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Qwen3.8-27B-Ridge-3.7bpw_empero.ai:latest
OLLAMA GGUFqwen35 · 27.3B · IQ2_M
Aug 27, 2026 · AMD Ryzen 7 9700X 8-Core Processor
Global Score
81 vs 75
Hardware Fit
82 vs 99
Quality Score
81 vs 64
Hardware
gemma4:12b-mlx Qwen3.8-27B-Ridge-…
MachineMacBook ProMicro-Star International Co., Ltd. MS-7E51
CPUApple M2 ProAMD Ryzen 7 9700X 8-Core Processor
Cores1016
RAM16 GB31 GB
GPUApple M2 ProNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSmacOS 26.5Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:12b-mlx Qwen3.8-27B-Ridge-…
Tokens/sec25.360.3
First chunk761 ms154 ms
TTFT7.7 s154 ms
Load time3.6 s0.0 s
Memory usage7.1 GB11.0 GB
Memory %44%35%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
Qwen3.8-27B-Ridge-3.7bp…
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
gemma4:12b-mlx
Reasoning
16/20
Coding
15/20
Instruction
12/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Qwen3.8-27B-Ridge-3.7bp…
Reasoning
20/20
Coding
17/20
Instruction
6/20
Structured
1/15
Math
14/15
Multilingual
6/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Adequate
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