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

gemma4:latest

OLLAMA GGUF

gemma4 · 8.0B · Q4_K_M

Excellent

Jul 11, 2026 · AMD Ryzen 9 9950X 16-Core Processor

Global Score
66 vs 87
Hardware Fit
100 vs 75
Quality Score
52 vs 92

Hardware

hf.co/empero-ai/Qw… gemma4:latest
MachineMacBook ProMicro-Star International Co., Ltd. MS-7E47
CPUApple M1 ProAMD Ryzen 9 9950X 16-Core Processor
Cores1032
RAM16 GB125 GB
GPUApple M1 ProAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 4080 SUPER
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.26100
Archarm64x64
Power Modebalancedbalanced

Performance

hf.co/empero-ai/Qw… gemma4:latest
Tokens/sec40.242.4
First chunk325 ms472 ms
TTFT325 ms3.8 s
Load time3.1 s0.3 s
Memory usage4.7 GB12.3 GB
Memory %30%10%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

gemma4:latest

Speed
40/50
TTFT
5/20
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

gemma4:latest

Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View hf.co/empero-ai/Qw… details | View gemma4: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