qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
Gemma4-26B:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
53 vs 87
Hardware Fit
72 vs 81
Quality Score
45 vs 89
Hardware
qwen3.5:9b Gemma4-26B:26b
MachineMacBook ProGMKtec NucBox EVO-T2S
CPUApple M1 MaxIntel Core™ Ultra X7 358H
Cores1016
RAM32 GB64 GB
GPUApple M1 MaxIntel(R) Arc(TM) B390 GPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.5:9b Gemma4-26B:26b
Tokens/sec18.623.1
First chunk403 ms978 ms
TTFT10.2 s978 ms
Load time4.3 s14.7 s
Memory usage9.1 GB16.7 GB
Memory %28%26%
HW Fit Score Breakdown
qwen3.5:9b
Speed
38/50
TTFT
4/20
Memory
30/30
Gemma4-26B:26b
Speed
31/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5:9b
Reasoning
12/20
Coding
3/20
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:26b
Reasoning
16/20
Coding
19/20
Instruction
17/20
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