Back to leaderboard

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

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 23, 2026 · Apple M1 Pro

orcarouter/Qwen3.8-27B-Uncensored:iq4_xs

OLLAMA GGUF

qwen35 · 27.3B · IQ4_XS

Excellent

Sep 11, 2026 · Intel Core™ i5-10400

Global Score
66 vs 88
Hardware Fit
100 vs 69
Quality Score
52 vs 96

Hardware

hf.co/empero-ai/Qw… orcarouter/Qwen3.8…
MachineMacBook ProASUS
CPUApple M1 ProIntel Core™ i5-10400
Cores1012
RAM16 GB16 GB
GPUApple M1 ProTodesk Virtual Display Adapter, AskLink Display Adapter (SDR), OrayIddDriver Device, NVIDIA GeForce RTX 3080
OSmacOS 26.6.2Microsoft Windows 10 专业版 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

hf.co/empero-ai/Qw… orcarouter/Qwen3.8…
Tokens/sec40.439.5
First chunk93 ms220 ms
TTFT93 ms3.2 s
Load time2.7 s13.7 s
Memory usage4.7 GB14.2 GB
Memory %30%89%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

orcarouter/Qwen3.8-27B-…

Speed
50/50
TTFT
14/20
Memory
5/30

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

orcarouter/Qwen3.8-27B-…

Reasoning
19/20
Coding
19/20
Instruction
18/20
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 orcarouter/Qwen3.8… 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