gemma4:12b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
glm-4.7-flash:q4_K_M
OLLAMA GGUFglm4moelite · 29.9B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
Global Score
71 vs 81
Hardware Fit
76 vs 89
Quality Score
69 vs 77
Hardware
gemma4:12b-mlx glm-4.7-flash:q4_K_M
MachineMacBook ProASUS
CPUApple M1 ProIntel Core™ i5-14600KF
Cores1020
RAM16 GB32 GB
GPUApple M1 ProNVIDIA GeForce RTX 4070 Ti SUPER
OSmacOS 26.6.2Microsoft Windows 11 Famille 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:12b-mlx glm-4.7-flash:q4_K_M
Tokens/sec25.035.1
First chunk787 ms440 ms
TTFT30.0 s440 ms
Load time4.0 s11.6 s
Memory usage7.1 GB18.4 GB
Memory %45%58%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
0/20
Memory
26/30
glm-4.7-flash:q4_K_M
Speed
49/50
TTFT
20/20
Memory
20/30
Quality
gemma4:12b-mlx
Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong
glm-4.7-flash:q4_K_M
Reasoning
13/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong 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