hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_S

OLLAMA GGUF

qwen35 · 27.3B · unknown

Marginal

Aug 25, 2026 · Apple M1 Pro

hf.co/bartowski/ai9stars_G9v3-3B-GGUF:BF16

OLLAMA GGUF

llama · 2.99B · BF16

Good

Aug 23, 2026 · Apple M1 Pro

Global Score

46 vs 64

Hardware Fit

50 vs 92

Quality Score

44 vs 52

Hardware

hf.co/unsloth/Qwen… hf.co/bartowski/ai…

MachineMacBook ProMacBook Pro

CPUApple M1 ProApple M1 Pro

Cores1010

RAM16 GB16 GB

GPUApple M1 ProApple M1 Pro

OSmacOS 26.6.2macOS 26.6.2

Archarm64arm64

Power Modebalancedbalanced

Performance

hf.co/unsloth/Qwen… hf.co/bartowski/ai…

Tokens/sec6.029.9

First chunk2377 ms100 ms

TTFT2.2 s100 ms

Load time6.8 s3.4 s

Memory usage10.6 GB8.9 GB

Memory %66%56%

HW Fit Score Breakdown

hf.co/unsloth/Qwen3.8-2…

Speed

15/50

TTFT

18/20

Memory

17/30

hf.co/bartowski/ai9star…

Speed

50/50

TTFT

20/20

Memory

22/30

Quality

hf.co/unsloth/Qwen3.8-2…

Reasoning

8/20

Coding

5/20

Instruction

10/20

Structured

11/15

Math

3/15

Multilingual

7/10

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

hf.co/bartowski/ai9star…

Reasoning

17/20

Coding

14/20

Instruction

6/20

Structured

0/15

Math

14/15

Multilingual

1/10

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

View hf.co/unsloth/Qwen… details | View hf.co/bartowski/ai… 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