mlx-community/quantized-gemma-2b-it
LM-STUDIO GGUFMar 5, 2026 · Apple M4
qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 4bit
Jul 17, 2026 · Apple M5 Max
Global Score
45 vs 89
Hardware Fit
100 vs 97
Quality Score
21 vs 86
Hardware
mlx-community/quan… qwen/qwen3.6-35b-a3b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M5 Max
Cores1018
RAM32 GB64 GB
GPUApple M4Apple M5 Max
OSmacOS 26.3macOS 27.0
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/quan… qwen/qwen3.6-35b-a3b
Tokens/sec44.4130.2
First chunk336 ms5 ms
TTFT336 ms135 ms
Load timeN/AN/A
Memory usage0.1 GB26.6 GB
Memory %0%42%
HW Fit Score Breakdown
mlx-community/quantized…
Speed
50/50
TTFT
20/20
Memory
30/30
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
mlx-community/quantized…
Reasoning
4/20
Coding
1/20
Instruction
9/20
Structured
4/15
Math
2/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Poor
qwen/qwen3.6-35b-a3b
Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest