gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Jul 7, 2026 · Cortex-X925
rnj-1:8b
OLLAMA GGUFgemma3 · 8.3B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
66 vs 80
Hardware Fit
40 vs 93
Quality Score
77 vs 74
Hardware
gemma4:31b rnj-1:8b
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
gemma4:31b rnj-1:8b
Tokens/sec10.722.3
First chunk983 ms404 ms
TTFT20.3 s404 ms
Load time8.8 s3.7 s
Memory usage21.4 GB8.3 GB
Memory %18%52%
HW Fit Score Breakdown
gemma4:31b
Speed
10/50
TTFT
0/20
Memory
30/30
rnj-1:8b
Speed
49/50
TTFT
20/20
Memory
24/30
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
rnj-1:8b
Reasoning
12/20
Coding
19/20
Instruction
15/20
Structured
5/15
Math
14/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Weak Math: Strong 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