Back to leaderboard

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

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

gemma-3-270m-it-qat-mlx

LM-STUDIO MLX

gemma3_text · 270M · 4bit

Marginal

Mar 4, 2026 · Apple M4

Global Score
36 vs 43
Hardware Fit
53 vs 99
Quality Score
28 vs 19

Hardware

deepseek-r1-distil… gemma-3-270m-it-qa…
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

deepseek-r1-distil… gemma-3-270m-it-qa…
Tokens/sec10.3344.2
First chunk27 ms173 ms
TTFT20.7 s173 ms
Load time15.4 sN/A
Memory usage1.0 GB0.3 GB
Memory %4%1%

HW Fit Score Breakdown

deepseek-r1-distill-qwe…

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

gemma-3-270m-it-qat-mlx

Speed
50/50
TTFT
20/20
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

gemma-3-270m-it-qat-mlx

Reasoning
4/20
Coding
0/20
Instruction
9/20
Structured
3/15
Math
1/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
View deepseek-r1-distil… details | View gemma-3-270m-it-qa… 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