qwen3:14b

qwen3 · 14.8B · Q4_K_M

THINKING MODEL

MacBook Pro (Apple M1 Max)

32 GB · macOS 26.3

Tested on March 5, 2026 · Submitted by alph0x

Top 71% Compare

Global Score

58 /100

Marginal

Hardware Fit

82/100

Quality

48/100

Get this model

🦙

Ollama

ollama pull qwen3:14b

View on Ollama Library

ollama.com/library/qwen3

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: MacBook Pro
CPU: Apple M1 Max
Cores: 10 total (8 perf + 2 eff)
Frequency: 2.4 GHz
RAM: 32 GB LPDDR5
GPU: Apple M1 Max
OS: macOS 26.3
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 24.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.2
First chunk latency Delay before the first streamed chunk arrives from runtime: 294 ms
Time to first token How fast the model starts responding — lower is better: 7.9 s
Load time Time to load the model into memory before inference: 3.7 s
Memory usage RAM consumed during inference — percentage of total system memory: 13.8 GB (43%)
Total tokens Total number of tokens generated across all benchmark prompts: 1419
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~891

Score breakdown

Speed

47/50

Time to first token

5/20

Memory

30/30

Quality

Reasoning

13/20

Coding

6/20

Instruction following

10/20

Structured output

9/15

Math

2/15

Multilingual

8/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.17.6
Model format: GGUF
Hardware profile: BALANCED
Result hash: 1510780988f80dac563624e63bc22d83b408f927ced37690a9fef2102851bc8e

Interpretation

Hardware fit: 82/100. Overall suitability: MARGINAL (Global 58/100). Category profile: Reasoning: Adequate, Coding: Weak, Instruction Following: Adequate, Structured Output: Adequate, Math: Poor, Multilingual: Strong.

Bench Environment

Power: AC CPU load: avg 25% (peak 28%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest