gemma3:12b
OLLAMA GGUFgemma3 · 12.2B · Q4_K_M
Mar 2, 2026 · Apple M4
qwen3-5-4b-q4-k-m
OLLAMA GGUFllama · 4B · Q4_K_M
Jul 9, 2026 · Intel Core™ i5-10400
Global Score
80 vs 83
Hardware Fit
83 vs 100
Quality Score
78 vs 76
Hardware
gemma3:12b qwen3-5-4b-q4-k-m
MachineMacBook AirMac Pro
CPUApple M4Intel Core™ i5-10400
Cores1012
RAM32 GB32 GB
GPUApple M4AMD Radeon RX 6700 XT
OSmacOS 26.3macOS 26.5.1
Archarm64x64
Power Modebalancedbalanced
Performance
gemma3:12b qwen3-5-4b-q4-k-m
Tokens/sec12.762.7
First chunkN/A278 ms
TTFT560 ms278 ms
Load time2.8 s0.0 s
Memory usage11.0 GB0.0 GB
Memory %34%0%
HW Fit Score Breakdown
gemma3:12b
Speed
23/50
TTFT
30/20
Memory
30/30
qwen3-5-4b-q4-k-m
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gemma3:12b
Reasoning
14/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
qwen3-5-4b-q4-k-m
Reasoning
14/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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