gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Jul 7, 2026 · Cortex-X925
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
94 vs 47
Hardware Fit
100 vs 67
Quality Score
92 vs 38
Hardware
gemma4:26b qwen3:8b
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
gemma4:26b qwen3:8b
Tokens/sec67.418.7
First chunk529 msN/A
TTFT529 ms12.1 s
Load time6.0 s1.2 s
Memory usage17.6 GB9.5 GB
Memory %15%30%
HW Fit Score Breakdown
gemma4:26b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3:8b
Speed
31/50
TTFT
6/20
Memory
30/30
Quality
gemma4:26b
Reasoning
18/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:8b
Reasoning
5/20
Coding
5/20
Instruction
4/20
Structured
12/15
Math
2/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Poor Structured Output: Strong Math: Poor 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