qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

Global Score

58 vs 82

Hardware Fit

82 vs 88

Quality Score

48 vs 80

Hardware

qwen3:14b unsloth-phi-4

MachineMacBook ProMac mini

CPUApple M1 MaxApple M4 Pro

Cores1014

RAM32 GB64 GB

GPUApple M1 MaxApple M4 Pro

OSmacOS 26.3macOS 15.7.4

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3:14b unsloth-phi-4

Tokens/sec24.427.4

First chunk294 ms457 ms

TTFT7.9 s457 ms

Load time3.7 sN/A

Memory usage13.8 GB7.7 GB

Memory %43%12%

HW Fit Score Breakdown

qwen3:14b

Speed

47/50

TTFT

5/20

Memory

30/30

unsloth-phi-4

Speed

38/50

TTFT

20/20

Memory

30/30

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

unsloth-phi-4

Reasoning

15/20

Coding

19/20

Instruction

14/20

Structured

13/15

Math

9/15

Multilingual

10/10

Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

View qwen3:14b details | View unsloth-phi-4 details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest