qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 4bit
Jul 17, 2026 · Apple M5 Max
qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
Global Score
89 vs 59
Hardware Fit
97 vs 63
Quality Score
86 vs 58
Hardware
qwen/qwen3.6-35b-a3b qwen3.8-27b-mlx
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
qwen/qwen3.6-35b-a3b qwen3.8-27b-mlx
Tokens/sec130.218.3
First chunk5 ms4 ms
TTFT135 ms530 ms
Load timeN/AN/A
Memory usage26.6 GB38.5 GB
Memory %42%60%
HW Fit Score Breakdown
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
27/30
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
Quality
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
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
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