gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
glm-4.7-flash:q4_K_M
OLLAMA GGUFglm4moelite · 29.9B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
Global Score
78 vs 81
Hardware Fit
47 vs 89
Quality Score
92 vs 77
Hardware
gemma4:31b glm-4.7-flash:q4_K_M
MachineAZW GTR ProASUS
CPUAMD RYZEN AI MAX+ 395Intel Core™ i5-14600KF
Cores3220
RAM125 GB32 GB
GPURadeon 8060SNVIDIA GeForce RTX 4070 Ti SUPER
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Famille 10.0.26200
Archx64x64
Power Modeperformancebalanced
Performance
gemma4:31b glm-4.7-flash:q4_K_M
Tokens/sec9.835.1
First chunk873 ms440 ms
TTFT873 ms440 ms
Load time7.0 s11.6 s
Memory usage68.3 GB18.4 GB
Memory %55%58%
HW Fit Score Breakdown
gemma4:31b
Speed
8/50
TTFT
16/20
Memory
23/30
glm-4.7-flash:q4_K_M
Speed
49/50
TTFT
20/20
Memory
20/30
Quality
gemma4:31b
Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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