Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Excellent

Aug 18, 2026 · Apple M4 Max

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

Global Score
81 vs 82
Hardware Fit
68 vs 88
Quality Score
87 vs 80

Hardware

qwen/qwen3.8-27b unsloth-phi-4
MachineMacBook ProMac mini
CPUApple M4 MaxApple M4 Pro
Cores1614
RAM128 GB64 GB
GPUApple M4 MaxApple M4 Pro
OSmacOS 26.5.2macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.8-27b unsloth-phi-4
Tokens/sec16.427.4
First chunk5 ms457 ms
TTFT742 ms457 ms
Load timeN/AN/A
Memory usage38.5 GB7.7 GB
Memory %30%12%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
18/50
TTFT
20/20
Memory
30/30

unsloth-phi-4

Speed
38/50
TTFT
20/20
Memory
30/30

Quality

qwen/qwen3.8-27b

Reasoning
17/20
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

unsloth-phi-4

Reasoning
15/20
Coding
19/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen/qwen3.8-27b details | View unsloth-phi-4 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