unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Oct 11, 2026 · AMD Ryzen 5 5500

Global Score

82 vs 74

Hardware Fit

88 vs 100

Quality Score

80 vs 63

Hardware

unsloth-phi-4 qwen3:0.6b

MachineMac miniMicrosoft WSL

CPUApple M4 ProAMD Ryzen 5 5500

Cores1412

RAM64 GB8 GB

GPUApple M4 ProIntegrated / Unknown

OSmacOS 15.7.4Ubuntu 26.04.1 LTS

Archarm64x64

Power Modebalancedunknown

Performance

unsloth-phi-4 qwen3:0.6b

Tokens/sec27.4257.7

First chunk457 ms92 ms

TTFT457 ms675 ms

Load timeN/A4.7 s

Memory usage7.7 GB0.9 GB

Memory %12%11%

HW Fit Score Breakdown

unsloth-phi-4

Speed

38/50

TTFT

20/20

Memory

30/30

qwen3:0.6b

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

unsloth-phi-4

Reasoning

15/20

Coding

19/20

Instruction

14/20

Structured

13/15

Math

9/15

Multilingual

10/10

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

qwen3:0.6b

Reasoning

13/20

Coding

6/20

Instruction

12/20

Structured

13/15

Math

12/15

Multilingual

7/10

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

View unsloth-phi-4 details | View qwen3:0.6b 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