qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
granite4.2:3b
OLLAMA GGUFgranite · 3.7B · Q4_K_M
Aug 29, 2026 · Apple M1 Pro
Global Score
68 vs 80
Hardware Fit
59 vs 80
Quality Score
72 vs 80
Hardware
qwen2.5-coder:7b granite4.2:3b
MachineASUSMacBook Pro
CPUIntel Gen Intel® Core™ i7-13700KApple M1 Pro
Cores2410
RAM64 GB16 GB
GPUNVIDIA GeForce RTX 3070Apple M1 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.6.2
Archx64arm64
Power Modeunknownbalanced
Performance
qwen2.5-coder:7b granite4.2:3b
Tokens/sec34.446.8
First chunk1991 ms135 ms
TTFT2.0 s135 ms
Load time40.6 s0.0 s
Memory usage5.0 GB12.7 GB
Memory %8%79%
HW Fit Score Breakdown
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
granite4.2:3b
Speed
50/50
TTFT
20/20
Memory
10/30
Quality
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
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
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