gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Jul 7, 2026 · Cortex-X925
starling-lm:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 6, 2026 · Apple M4
Global Score
66 vs 65
Hardware Fit
40 vs 96
Quality Score
77 vs 52
Hardware
gemma4:31b starling-lm:7b
MachineASUSTeK COMPUTER INC. GX10MacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced
Performance
gemma4:31b starling-lm:7b
Tokens/sec10.723.8
First chunk983 ms232 ms
TTFT20.3 s232 ms
Load time8.8 s0.4 s
Memory usage21.4 GB5.3 GB
Memory %18%17%
HW Fit Score Breakdown
gemma4:31b
Speed
10/50
TTFT
0/20
Memory
30/30
starling-lm:7b
Speed
46/50
TTFT
20/20
Memory
30/30
Quality
gemma4:31b
Reasoning
14/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
starling-lm:7b
Reasoning
10/20
Coding
13/20
Instruction
8/20
Structured
3/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Poor 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