Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 18, 2026 · Apple M4 Max

aya:8b

OLLAMA GGUF

command-r · 8.0B · F16

Good

Mar 1, 2026 · Apple M4

Global Score
87 vs 66
Hardware Fit
83 vs 92
Quality Score
88 vs 55

Hardware

qwen/qwen3.8-27b aya:8b
MachineMacBook ProMacBook Air
CPUApple M4 MaxApple M4
Cores1610
RAM128 GB32 GB
GPUApple M4 MaxApple M4
OSmacOS 26.5.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.8-27b aya:8b
Tokens/sec29.120.0
First chunk9 msN/A
TTFT650 ms300 ms
Load timeN/A0.9 s
Memory usage21.0 GB6.0 GB
Memory %16%19%

HW Fit Score Breakdown

qwen/qwen3.8-27b

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

aya:8b

Speed
32/50
TTFT
30/20
Memory
30/30

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

aya:8b

Reasoning
10/20
Coding
6/20
Instruction
13/20
Structured
15/15
Math
2/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen/qwen3.8-27b details | View aya:8b 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