Back to leaderboard

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

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 26, 2026 · Apple M1 Pro

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor

Global Score
66 vs 81
Hardware Fit
100 vs 100
Quality Score
52 vs 73

Hardware

hf.co/empero-ai/Qw… gemma3n:latest
MachineMacBook ProSupermicro AS -2015HS-TNR
CPUApple M1 ProAMD EPYC 9654P 96-Core Processor
Cores1064
RAM16 GB128 GB
GPUApple M1 ProGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSmacOS 26.6.2Ubuntu 24.04.3 LTS
Archarm64x64
Power Modebalancedperformance

Performance

hf.co/empero-ai/Qw… gemma3n:latest
Tokens/sec40.2108.7
First chunk101 ms333 ms
TTFT101 ms333 ms
Load time2.6 s4.5 s
Memory usage4.7 GB8.6 GB
Memory %30%7%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

gemma3n:latest

Speed
50/50
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

gemma3n:latest

Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View hf.co/empero-ai/Qw… details | View gemma3n:latest 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