hf.co/Edge-Quant/Nanbeige4.1-3B-Q8_0-GGUF:Q8_0

OLLAMA GGUF

llama · 3.93B · unknown

Not Rec.

Aug 22, 2026 · Apple M1 Pro

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

Global Score

52 vs 65

Hardware Fit

75 vs 96

Quality Score

42 vs 51

Hardware

hf.co/Edge-Quant/N… qwen3-4b-qwen3.6-p…

MachineMacBook ProMac Studio

CPUApple M1 ProApple M2 Max

Cores1012

RAM16 GB96 GB

GPUApple M1 ProApple M2 Max

OSmacOS 26.6.2macOS 26.1

Archarm64arm64

Power Modebalancedbalanced

Performance

hf.co/Edge-Quant/N… qwen3-4b-qwen3.6-p…

Tokens/sec43.599.6

First chunk225 ms18 ms

TTFT30.0 s1.6 s

Load time2.7 s4.8 s

Memory usage8.2 GB0.3 GB

Memory %51%0%

HW Fit Score Breakdown

hf.co/Edge-Quant/Nanbei…

Speed

50/50

TTFT

0/20

Memory

25/30

qwen3-4b-qwen3.6-plus-r…

Speed

50/50

TTFT

16/20

Memory

30/30

Quality

hf.co/Edge-Quant/Nanbei…

Reasoning

13/20

Coding

1/20

Instruction

7/20

Structured

1/15

Math

13/15

Multilingual

7/10

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

qwen3-4b-qwen3.6-plus-r…

Reasoning

8/20

Coding

4/20

Instruction

14/20

Structured

9/15

Math

8/15

Multilingual

8/10

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

View hf.co/Edge-Quant/N… details | View qwen3-4b-qwen3.6-p… 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