Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 18, 2026 · Apple M4 Max

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Excellent

Jul 17, 2026 · Apple M5 Max

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

Hardware

qwen/qwen3.8-27b qwen3.6:35b-mlx
MachineMacBook ProMacBook Pro
CPUApple M4 MaxApple M5 Max
Cores1618
RAM128 GB48 GB
GPUApple M4 MaxApple M5 Max
OSmacOS 26.5.2macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.8-27b qwen3.6:35b-mlx
Tokens/sec29.1129.4
First chunk9 ms49 ms
TTFT650 ms49 ms
Load timeN/A0.0 s
Memory usage21.0 GB20.5 GB
Memory %16%43%

HW Fit Score Breakdown

qwen/qwen3.8-27b

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

qwen3.6:35b-mlx

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

Quality

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

qwen3.6:35b-mlx

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
View qwen/qwen3.8-27b details | View qwen3.6:35b-mlx 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