qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 4bit
Jul 17, 2026 · Apple M5 Max
qwen3.5-0.8b-mlx
LM-STUDIO MLXqwen3_5 · 0.8B · 4bit
Mar 3, 2026 · Apple M4
Global Score
89 vs 55
Hardware Fit
97 vs 87
Quality Score
86 vs 41
Hardware
qwen/qwen3.6-35b-a3b qwen3.5-0.8b-mlx
MachineMacBook ProMacBook Air
CPUApple M5 MaxApple M4
Cores1810
RAM64 GB32 GB
GPUApple M5 MaxApple M4
OSmacOS 27.0macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3.6-35b-a3b qwen3.5-0.8b-mlx
Tokens/sec130.268.2
First chunk5 ms3268 ms
TTFT135 ms3.3 s
Load timeN/AN/A
Memory usage26.6 GB0.6 GB
Memory %42%2%
HW Fit Score Breakdown
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
27/30
qwen3.5-0.8b-mlx
Speed
50/50
TTFT
13/20
Memory
24/30
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
qwen3.5-0.8b-mlx
Reasoning
8/20
Coding
1/20
Instruction
12/20
Structured
12/15
Math
3/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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