Back to leaderboard

hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 22, 2026 · Apple M1 Pro

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

Global Score
66 vs 82
Hardware Fit
100 vs 88
Quality Score
52 vs 80

Hardware

hf.co/empero-ai/Qw… unsloth-phi-4
MachineMacBook ProMac mini
CPUApple M1 ProApple M4 Pro
Cores1014
RAM16 GB64 GB
GPUApple M1 ProApple M4 Pro
OSmacOS 26.6.2macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

hf.co/empero-ai/Qw… unsloth-phi-4
Tokens/sec40.227.4
First chunk325 ms457 ms
TTFT325 ms457 ms
Load time3.1 sN/A
Memory usage4.7 GB7.7 GB
Memory %30%12%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

unsloth-phi-4

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

Quality

hf.co/empero-ai/Qwen3.8…

Reasoning
15/20
Coding
9/20
Instruction
8/20
Structured
1/15
Math
15/15
Multilingual
4/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

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 hf.co/empero-ai/Qw… 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