Back to leaderboard

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

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

Global Score
36 vs 58
Hardware Fit
53 vs 68
Quality Score
28 vs 54

Hardware

deepseek-r1-distil… qwen3.5-9b-mlx
MachineMac miniMac mini
CPUApple M4Apple M4
Cores1010
RAM24 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

deepseek-r1-distil… qwen3.5-9b-mlx
Tokens/sec10.316.7
First chunk27 ms23 ms
TTFT20.7 s14.1 s
Load time15.4 sN/A
Memory usage1.0 GB7.8 GB
Memory %4%33%

HW Fit Score Breakdown

deepseek-r1-distill-qwe…

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

qwen3.5-9b-mlx

Speed
36/50
TTFT
3/20
Memory
29/30

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

qwen3.5-9b-mlx

Reasoning
10/20
Coding
16/20
Instruction
4/20
Structured
9/15
Math
10/15
Multilingual
5/10
Reasoning: Adequate Coding: Strong Instruction Following: Poor Structured Output: Adequate Math: Adequate Multilingual: Adequate
View deepseek-r1-distil… details | View qwen3.5-9b-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