qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
stablelm-2-zephyr-1.6b
LM-STUDIO GGUFstablelm · 1.6B · Q4_K_M
Mar 6, 2026 · Intel Core™ i5-5300U
Global Score
58 vs 35
Hardware Fit
82 vs 61
Quality Score
48 vs 24
Hardware
qwen3:14b stablelm-2-zephyr-…
MachineMacBook ProLENOVO 20BUS00700
CPUApple M1 MaxIntel Core™ i5-5300U
Cores104
RAM32 GB16 GB
GPUApple M1 MaxIntel(R) HD Graphics 5500
OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3:14b stablelm-2-zephyr-…
Tokens/sec24.46.5
First chunk294 ms3080 ms
TTFT7.9 s3.1 s
Load time3.7 sN/A
Memory usage13.8 GB1.0 GB
Memory %43%6%
HW Fit Score Breakdown
qwen3:14b
Speed
47/50
TTFT
5/20
Memory
30/30
stablelm-2-zephyr-1.6b
Speed
23/50
TTFT
16/20
Memory
22/30
Quality
qwen3:14b
Reasoning
13/20
Coding
6/20
Instruction
10/20
Structured
9/15
Math
2/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Strong
stablelm-2-zephyr-1.6b
Reasoning
2/20
Coding
2/20
Instruction
8/20
Structured
6/15
Math
2/15
Multilingual
4/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
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