gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jul 7, 2026 · Cortex-X925
qwen3.5:4b-mlx
OLLAMA GGUFnvfp4
Aug 25, 2026 · Apple M1 Pro
Global Score
86 vs 68
Hardware Fit
79 vs 91
Quality Score
89 vs 58
Hardware
gemma4:12b qwen3.5:4b-mlx
MachineASUSTeK COMPUTER INC. GX10MacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced
Performance
gemma4:12b qwen3.5:4b-mlx
Tokens/sec27.542.2
First chunk484 ms201 ms
TTFT484 ms4.4 s
Load time8.2 s0.0 s
Memory usage9.3 GB3.8 GB
Memory %8%24%
HW Fit Score Breakdown
gemma4:12b
Speed
29/50
TTFT
20/20
Memory
30/30
qwen3.5:4b-mlx
Speed
50/50
TTFT
11/20
Memory
30/30
Quality
gemma4:12b
Reasoning
17/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.5:4b-mlx
Reasoning
16/20
Coding
2/20
Instruction
13/20
Structured
7/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate 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