vicuna:13b
OLLAMA GGUFllama · 13B · Q4_0
Mar 1, 2026 · Apple M4
qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
Global Score
59 vs 68
Hardware Fit
84 vs 59
Quality Score
48 vs 72
Hardware
vicuna:13b qwen2.5-coder:7b
MachineMacBook AirASUS
CPUApple M4Intel Gen Intel® Core™ i7-13700K
Cores1024
RAM32 GB64 GB
GPUApple M4NVIDIA GeForce RTX 3070
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown
Performance
vicuna:13b qwen2.5-coder:7b
Tokens/sec13.434.4
First chunkN/A1991 ms
TTFT438 ms2.0 s
Load time0.6 s40.6 s
Memory usage10.3 GB5.0 GB
Memory %32%8%
HW Fit Score Breakdown
vicuna:13b
Speed
24/50
TTFT
30/20
Memory
30/30
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
Quality
vicuna:13b
Reasoning
7/20
Coding
5/20
Instruction
12/20
Structured
13/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor 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