gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jul 4, 2026 · Apple M2 Pro
qwen3:1.7b
OLLAMA GGUFqwen3 · 2.0B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
Global Score
89 vs 72
Hardware Fit
88 vs 92
Quality Score
89 vs 63
Hardware
gemma4:12b qwen3:1.7b
MachineMacBook ProAZW GTR Pro
CPUApple M2 ProAMD RYZEN AI MAX+ 395
Cores1032
RAM16 GB125 GB
GPUApple M2 ProAMD Radeon 8060S
OSmacOS 26.5Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
gemma4:12b qwen3:1.7b
Tokens/sec18.5120.7
First chunk752 ms93 ms
TTFT752 ms1.5 s
Load time6.1 s2.5 s
Memory usage7.5 GB5.8 GB
Memory %47%5%
HW Fit Score Breakdown
gemma4:12b
Speed
42/50
TTFT
20/20
Memory
26/30
qwen3:1.7b
Speed
50/50
TTFT
12/20
Memory
30/30
Quality
gemma4:12b
Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:1.7b
Reasoning
13/20
Coding
6/20
Instruction
13/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak 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