qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 6bit
Jul 17, 2026 · Apple M5 Max
Global Score
59 vs 87
Hardware Fit
63 vs 90
Quality Score
58 vs 86
Hardware
qwen3.8-27b-mlx qwen/qwen3.6-35b-a3b
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M5 Max
Cores1818
RAM64 GB64 GB
GPUApple M5 MaxApple M5 Max
OSmacOS 27.0macOS 27.0
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.8-27b-mlx qwen/qwen3.6-35b-a3b
Tokens/sec18.386.5
First chunk4 ms9 ms
TTFT530 ms175 ms
Load timeN/AN/A
Memory usage38.5 GB37.9 GB
Memory %60%59%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
20/30
Quality
qwen3.8-27b-mlx
Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
qwen/qwen3.6-35b-a3b
Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong 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