qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
phi3:14b
OLLAMA GGUFphi3 · 14.0B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
68 vs 63
Hardware Fit
59 vs 83
Quality Score
72 vs 55
Hardware
qwen2.5-coder:7b phi3:14b
MachineASUSMacBook Air
CPUIntel Gen Intel® Core™ i7-13700KApple M4
Cores2410
RAM64 GB32 GB
GPUNVIDIA GeForce RTX 3070Apple M4
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3
Archx64arm64
Power Modeunknownbalanced
Performance
qwen2.5-coder:7b phi3:14b
Tokens/sec34.412.7
First chunk1991 msN/A
TTFT2.0 s434 ms
Load time40.6 s0.9 s
Memory usage5.0 GB17.7 GB
Memory %8%55%
HW Fit Score Breakdown
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
phi3:14b
Speed
23/50
TTFT
30/20
Memory
30/30
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
phi3:14b
Reasoning
14/20
Coding
2/20
Instruction
14/20
Structured
7/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Weak 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