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

google/gemma-3-27b

LM-STUDIO MLX

gemma3 · 27B · 4bit

Not Rec.

Mar 19, 2026 · Apple M4

Global Score
66 vs 71
Hardware Fit
100 vs 35
Quality Score
52 vs 86

Hardware

hf.co/empero-ai/Qw… google/gemma-3-27b
MachineMacBook ProMac mini
CPUApple M1 ProApple M4
Cores1010
RAM16 GB24 GB
GPUApple M1 ProApple M4
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

hf.co/empero-ai/Qw… google/gemma-3-27b
Tokens/sec40.45.9
First chunk93 ms19 ms
TTFT93 ms1.8 s
Load time2.7 sN/A
Memory usage4.7 GB22.0 GB
Memory %30%92%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

google/gemma-3-27b

Speed
12/50
TTFT
19/20
Memory
4/30

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

google/gemma-3-27b

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View hf.co/empero-ai/Qw… details | View google/gemma-3-27b 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