qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

Global Score

64 vs 82

Hardware Fit

69 vs 88

Quality Score

62 vs 80

Hardware

qwen3.5:4b unsloth-phi-4

MachineLENOVO 20U30029MBMac mini

CPUIntel Core™ i5-10210UApple M4 Pro

Cores814

RAM15 GB64 GB

GPUCometLake-U GT2 [UHD Graphics]Apple M4 Pro

OSPop 24.04 LTSmacOS 15.7.4

Archx64arm64

Power Modeperformancebalanced

Performance

qwen3.5:4b unsloth-phi-4

Tokens/sec7.427.4

First chunk1815 ms457 ms

TTFT1.8 s457 ms

Load time10.9 sN/A

Memory usage3.5 GB7.7 GB

Memory %23%12%

HW Fit Score Breakdown

qwen3.5:4b

Speed

19/50

TTFT

20/20

Memory

30/30

unsloth-phi-4

Speed

38/50

TTFT

20/20

Memory

30/30

Quality

qwen3.5:4b

Reasoning

15/20

Coding

14/20

Instruction

6/20

Structured

12/15

Math

6/15

Multilingual

9/10

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

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

View qwen3.5:4b details | View unsloth-phi-4 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