Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 4bit

Excellent

Jul 17, 2026 · Apple M5 Max

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 18, 2026 · Apple M4 Max

Global Score
89 vs 87
Hardware Fit
97 vs 83
Quality Score
86 vs 88

Hardware

qwen/qwen3.6-35b-a3b qwen/qwen3.8-27b
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M4 Max
Cores1816
RAM64 GB128 GB
GPUApple M5 MaxApple M4 Max
OSmacOS 27.0macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.6-35b-a3b qwen/qwen3.8-27b
Tokens/sec130.229.1
First chunk5 ms9 ms
TTFT135 ms650 ms
Load timeN/AN/A
Memory usage26.6 GB21.0 GB
Memory %42%16%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

Speed
50/50
TTFT
20/20
Memory
27/30

qwen/qwen3.8-27b

Speed
33/50
TTFT
20/20
Memory
30/30

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

qwen/qwen3.8-27b

Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen/qwen3.6-35b-a3b details | View qwen/qwen3.8-27b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest