qwen3.8-27b-mlx
LM-STUDIO UNKNOWN27B
Aug 17, 2026 · Apple M5 Max
qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
Global Score
66 vs 80
Hardware Fit
91 vs 77
Quality Score
55 vs 81
Hardware
qwen3.8-27b-mlx qwen3.6:35b-mlx
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M5 Max
Cores1818
RAM64 GB48 GB
GPUApple M5 MaxApple M5 Max
OSmacOS 27.0macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.8-27b-mlx qwen3.6:35b-mlx
Tokens/sec33.2129.8
First chunk7 ms77 ms
TTFT311 ms30.0 s
Load timeN/A1.8 s
Memory usage0.5 GB19.7 GB
Memory %1%41%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
41/50
TTFT
20/20
Memory
30/30
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
Quality
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
qwen3.6:35b-mlx
Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate 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