deepseek-r1-distill-qwen-14b-mlx

qwen2 · 14B · 5bit

THINKING MODEL

Mac mini (Apple M4)

24 GB · macOS 26.3

Tested on March 11, 2026 · Submitted by cryptoepops

Top 94% Compare

Global Score

36 /100

Not Rec.

Hardware Fit

53/100

Quality

28/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: Mac mini
CPU: Apple M4
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 24 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 10.3
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.0
First chunk latency Delay before the first streamed chunk arrives from runtime: 27 ms
Time to first token How fast the model starts responding — lower is better: 20.7 s
Load time Time to load the model into memory before inference: 15.4 s
Memory usage RAM consumed during inference — percentage of total system memory: 1.0 GB (4%)
Total tokens Total number of tokens generated across all benchmark prompts: 1621
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~959

Score breakdown

Speed

23/50

Time to first token

0/20

Memory

30/30

Quality

Reasoning

3/20

Coding

6/20

Instruction following

6/20

Structured output

3/15

Math

2/15

Multilingual

8/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.6+1
Model format: MLX
Hardware profile: ENTRY
Result hash: 8facd3ad7d5e2e68152880b87796ceca928d463d9d118405317d6d25a158d6c7

Interpretation

Hardware fit: 53/100. Overall suitability: NOT RECOMMENDED (Global 36/100). Category profile: Reasoning: Poor, Coding: Weak, Instruction Following: Weak, Structured Output: Poor, Math: Poor, Multilingual: Strong.

Bench Environment

Power: AC CPU load: avg 13% (peak 18%)

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