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

unsloth/gemma-4-e2b-it@q8_0

LM-STUDIO GGUF

gemma4 · Q8_0

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
76 vs 75
Hardware Fit
100 vs 74
Quality Score
66 vs 76

Hardware

hf.co/empero-ai/Qw… unsloth/gemma-4-e2…
MachineMacBook ProDocker Container
CPUApple M1 ProIntel Gen Intel® Core™ i9-11900H
Cores1016
RAM16 GB15 GB
GPUApple M1 ProTigerLake-H GT1 [UHD Graphics]
OSmacOS 26.6.2Ubuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance

Performance

hf.co/empero-ai/Qw… unsloth/gemma-4-e2…
Tokens/sec40.313.0
First chunk101 ms62 ms
TTFT101 ms1.5 s
Load time2.7 s7.8 s
Memory usage4.5 GB0.0 GB
Memory %28%0%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

unsloth/gemma-4-e2b-it@…

Speed
24/50
TTFT
20/20
Memory
30/30

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

unsloth/gemma-4-e2b-it@…

Reasoning
11/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View hf.co/empero-ai/Qw… details | View unsloth/gemma-4-e2… 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