qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Jul 7, 2026 · Cortex-X925
Global Score
58 vs 94
Hardware Fit
79 vs 100
Quality Score
49 vs 92
Hardware
qwen3.5:9b gemma4:26b
MachineMacBook ProASUSTeK COMPUTER INC. GX10
CPUApple M1 ProCortex-X925
Cores1020
RAM16 GB122 GB
GPUApple M1 ProDevice 2e12
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
qwen3.5:9b gemma4:26b
Tokens/sec22.167.4
First chunk601 ms529 ms
TTFT9.1 s529 ms
Load time4.2 s6.0 s
Memory usage7.2 GB17.6 GB
Memory %45%15%
HW Fit Score Breakdown
qwen3.5:9b
Speed
48/50
TTFT
5/20
Memory
26/30
gemma4:26b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5:9b
Reasoning
15/20
Coding
4/20
Instruction
5/20
Structured
6/15
Math
11/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong
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
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