glm-4.7-flash:latest
OLLAMA GGUFglm4moelite · 29.9B · Q4_K_M
Mar 27, 2026 · AMD RYZEN AI MAX+ 395
gemma4:12b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
Global Score
83 vs 71
Hardware Fit
100 vs 76
Quality Score
76 vs 69
Hardware
glm-4.7-flash:latest gemma4:12b-mlx
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M1 Pro
Cores3210
RAM125 GB16 GB
GPURadeon 8060SApple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archx64arm64
Power Modeperformancebalanced
Performance
glm-4.7-flash:latest gemma4:12b-mlx
Tokens/sec58.025.0
First chunk268 ms787 ms
TTFT268 ms30.0 s
Load time7.8 s4.0 s
Memory usage37.7 GB7.1 GB
Memory %30%45%
HW Fit Score Breakdown
glm-4.7-flash:latest
Speed
50/50
TTFT
20/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
0/20
Memory
26/30
Quality
glm-4.7-flash:latest
Reasoning
13/20
Coding
17/20
Instruction
11/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
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
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