granite4.2:3b
OLLAMA GGUFgranite · 3.7B · Q4_K_M
Aug 29, 2026 · Apple M1 Pro
qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
Global Score
80 vs 68
Hardware Fit
80 vs 59
Quality Score
80 vs 72
Hardware
granite4.2:3b qwen2.5-coder:7b
MachineMacBook ProASUS
CPUApple M1 ProIntel Gen Intel® Core™ i7-13700K
Cores1024
RAM16 GB64 GB
GPUApple M1 ProNVIDIA GeForce RTX 3070
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown
Performance
granite4.2:3b qwen2.5-coder:7b
Tokens/sec46.834.4
First chunk135 ms1991 ms
TTFT135 ms2.0 s
Load time0.0 s40.6 s
Memory usage12.7 GB5.0 GB
Memory %79%8%
HW Fit Score Breakdown
granite4.2:3b
Speed
50/50
TTFT
20/20
Memory
10/30
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
Quality
granite4.2:3b
Reasoning
18/20
Coding
13/20
Instruction
12/20
Structured
15/15
Math
14/15
Multilingual
8/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen2.5-coder:7b
Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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