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

qwen35 · 1.94B · BF16

MacBook Pro (Apple M1 Pro)

16 GB · macOS 26.6.2

Tested on August 22, 2026

Top 69% Compare

Global Score

66 /100

Good

Hardware Fit

100/100

Quality

52/100

Get this model

🦙

Ollama

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

View on Ollama Library

ollama.com/library/hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: MacBook Pro
CPU: Apple M1 Pro
Cores: 10 total (8 perf + 2 eff)
Frequency: 2.4 GHz
RAM: 16 GB LPDDR5
GPU: Apple M1 Pro
OS: macOS 26.6.2
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 40.2
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.1
First chunk latency Delay before the first streamed chunk arrives from runtime: 325 ms
Time to first token How fast the model starts responding — lower is better: 325 ms
Load time Time to load the model into memory before inference: 3.1 s
Memory usage RAM consumed during inference — percentage of total system memory: 4.7 GB (30%)
Total tokens Total number of tokens generated across all benchmark prompts: 1118

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

15/20

Coding

9/20

Instruction following

8/20

Structured output

1/15

Math

15/15

Multilingual

4/10

Category levels

Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.32.14
Model format: GGUF
Hardware profile: ENTRY
Result hash: 11487bf5b80909a6b5cb907497b46afe2b256c6c17eac4ffe2e726b4f2369611

Interpretation

Hardware fit: 100/100. Overall suitability: GOOD (Global 66/100). Category profile: Reasoning: Adequate, Coding: Weak, Instruction Following: Weak, Structured Output: Poor, Math: Strong, Multilingual: Weak.

Bench Environment

Power: AC CPU load: avg 37% (peak 40%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest