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

laguna-xs-2.1

OLLAMA GGUF
Excellent

Aug 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score
66 vs 84
Hardware Fit
100 vs 100
Quality Score
52 vs 77

Hardware

hf.co/empero-ai/Qw… laguna-xs-2.1
MachineMacBook ProAZW GTR Pro
CPUApple M1 ProAMD RYZEN AI MAX+ 395
Cores1032
RAM16 GB125 GB
GPUApple M1 ProRadeon 8060S
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

hf.co/empero-ai/Qw… laguna-xs-2.1
Tokens/sec40.265.9
First chunk101 ms281 ms
TTFT101 ms281 ms
Load time2.6 s9.9 s
Memory usage4.7 GB30.1 GB
Memory %30%24%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

laguna-xs-2.1

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

laguna-xs-2.1

Reasoning
8/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
11/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View hf.co/empero-ai/Qw… details | View laguna-xs-2.1 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