Back to leaderboard

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

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

gemma4:e4b-mlx

OLLAMA GGUF
Not Rec.

Jul 7, 2026 · Apple M2 Pro

Global Score
36 vs 78
Hardware Fit
53 vs 72
Quality Score
28 vs 81

Hardware

deepseek-r1-distil… gemma4:e4b-mlx
MachineMac miniMacBook Pro
CPUApple M4Apple M2 Pro
Cores1010
RAM24 GB16 GB
GPUApple M4Apple M2 Pro
OSmacOS 26.3macOS 26.5
Archarm64arm64
Power Modebalancedbalanced

Performance

deepseek-r1-distil… gemma4:e4b-mlx
Tokens/sec10.326.9
First chunk27 ms222 ms
TTFT20.7 s222 ms
Load time15.4 s0.1 s
Memory usage1.0 GB15.4 GB
Memory %4%96%

HW Fit Score Breakdown

deepseek-r1-distill-qwe…

Speed
23/50
TTFT
0/20
Memory
30/30

gemma4:e4b-mlx

Speed
50/50
TTFT
20/20
Memory
2/30

Quality

deepseek-r1-distill-qwe…

Reasoning
3/20
Coding
6/20
Instruction
6/20
Structured
3/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Strong

gemma4:e4b-mlx

Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View deepseek-r1-distil… details | View gemma4:e4b-mlx 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