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

mlx-community/meta-llama-3.1-8b-instruct

LM-STUDIO MLX

llama · 8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

Global Score
66 vs 77
Hardware Fit
100 vs 100
Quality Score
52 vs 67

Hardware

hf.co/empero-ai/Qw… mlx-community/meta…
MachineMacBook ProMac mini
CPUApple M1 ProApple M4 Pro
Cores1014
RAM16 GB64 GB
GPUApple M1 ProApple M4 Pro
OSmacOS 26.6.2macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

hf.co/empero-ai/Qw… mlx-community/meta…
Tokens/sec40.254.3
First chunk101 ms277 ms
TTFT101 ms277 ms
Load time2.6 sN/A
Memory usage4.7 GB4.2 GB
Memory %30%7%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

mlx-community/meta-llam…

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

mlx-community/meta-llam…

Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View hf.co/empero-ai/Qw… details | View mlx-community/meta… 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