Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 18, 2026 · Apple M4 Max

mlx-community/Yi-1.5-6B-Chat-4bit

LM-STUDIO GGUF
Good

Mar 5, 2026 · Apple M4

Global Score
87 vs 73
Hardware Fit
83 vs 100
Quality Score
88 vs 62

Hardware

qwen/qwen3.8-27b mlx-community/Yi-1…
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 mlx-community/Yi-1…
Tokens/sec29.129.1
First chunk9 ms451 ms
TTFT650 ms451 ms
Load timeN/AN/A
Memory usage21.0 GB0.9 GB
Memory %16%3%

HW Fit Score Breakdown

qwen/qwen3.8-27b

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

mlx-community/Yi-1.5-6B…

Speed
50/50
TTFT
20/20
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

mlx-community/Yi-1.5-6B…

Reasoning
10/20
Coding
11/20
Instruction
13/20
Structured
13/15
Math
9/15
Multilingual
6/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Adequate

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