hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ2_XXS

OLLAMA GGUF

qwen35 · 27.3B · unknown

Not Rec.

Aug 22, 2026 · Apple M1 Pro

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score

31 vs 62

Hardware Fit

37 vs 99

Quality Score

28 vs 46

Hardware

hf.co/unsloth/Qwen… microsoft/phi-4-mi…

MachineMacBook ProMacBook Air

CPUApple M1 ProApple M4

Cores1010

RAM16 GB32 GB

GPUApple M1 ProApple M4

OSmacOS 26.6.2macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

hf.co/unsloth/Qwen… microsoft/phi-4-mi…

Tokens/sec5.440.3

First chunk5076 ms289 ms

TTFT5.1 s289 ms

Load time0.3 sN/A

Memory usage11.6 GB2.0 GB

Memory %72%6%

HW Fit Score Breakdown

hf.co/unsloth/Qwen3.8-2…

Speed

13/50

TTFT

10/20

Memory

14/30

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

29/30

Quality

hf.co/unsloth/Qwen3.8-2…

Reasoning

9/20

Coding

2/20

Instruction

1/20

Structured

1/15

Math

9/15

Multilingual

6/10

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

microsoft/phi-4-mini-re…

Reasoning

7/20

Coding

6/20

Instruction

7/20

Structured

7/15

Math

12/15

Multilingual

7/10

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

View hf.co/unsloth/Qwen… details | View microsoft/phi-4-mi… 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