Back to leaderboard

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

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 25, 2026 · Apple M1 Pro

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score
76 vs 62
Hardware Fit
100 vs 99
Quality Score
66 vs 46

Hardware

hf.co/empero-ai/Qw… microsoft/phi-4-mi…
MachineMacBook ProMacBook Air
CPUApple M1 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M1 ProApple M4
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

hf.co/empero-ai/Qw… microsoft/phi-4-mi…
Tokens/sec40.340.3
First chunk101 ms289 ms
TTFT101 ms289 ms
Load time2.7 sN/A
Memory usage4.5 GB2.0 GB
Memory %28%6%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

microsoft/phi-4-mini-re…

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

hf.co/empero-ai/Qwen3.8…

Reasoning
11/20
Coding
10/20
Instruction
12/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

microsoft/phi-4-mini-re…

Reasoning
7/20
Coding
6/20
Instruction
7/20
Structured
7/15
Math
12/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate
View hf.co/empero-ai/Qw… details | View microsoft/phi-4-mi… 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