mlx-community/quantized-gemma-2b-it
LM-STUDIO GGUFMar 5, 2026 · Apple M4
qwen3.8-27b-mlx
LM-STUDIO UNKNOWN27B
Aug 17, 2026 · Apple M5 Max
Global Score
45 vs 66
Hardware Fit
100 vs 91
Quality Score
21 vs 55
Hardware
mlx-community/quan… qwen3.8-27b-mlx
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… qwen3.8-27b-mlx
Tokens/sec44.433.2
First chunk336 ms7 ms
TTFT336 ms311 ms
Load timeN/AN/A
Memory usage0.1 GB0.5 GB
Memory %0%1%
HW Fit Score Breakdown
mlx-community/quantized…
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.8-27b-mlx
Speed
41/50
TTFT
20/20
Memory
30/30
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
qwen3.8-27b-mlx
Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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