Back to leaderboard

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

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

qwen3-coder:30b-a3b-q8_0

OLLAMA GGUF

qwen3moe · 30.5B · Q8_0

Good

Jun 18, 2026 · AMD Ryzen 5 5500U

Global Score
36 vs 78
Hardware Fit
53 vs 54
Quality Score
28 vs 88

Hardware

deepseek-r1-distil… qwen3-coder:30b-a3…
MachineMac miniHP HP Pavilion Laptop 15-eh1xxx
CPUApple M4AMD Ryzen 5 5500U
Cores1012
RAM24 GB63 GB
GPUApple M4AMD Radeon(TM) Graphics
OSmacOS 26.3Microsoft Windows 10 Enterprise LTSC 10.0.19044
Archarm64x64
Power Modebalancedbalanced

Performance

deepseek-r1-distil… qwen3-coder:30b-a3…
Tokens/sec10.38.0
First chunk27 ms1468 ms
TTFT20.7 s1.5 s
Load time15.4 s114.5 s
Memory usage1.0 GB33.5 GB
Memory %4%53%

HW Fit Score Breakdown

deepseek-r1-distill-qwe…

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

qwen3-coder:30b-a3b-q8_0

Speed
11/50
TTFT
19/20
Memory
24/30

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-coder:30b-a3b-q8_0

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View deepseek-r1-distil… details | View qwen3-coder:30b-a3… 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