qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M4

deepseek-coder-1.3b-instruct

LM-STUDIO GGUF

llama · 1.3B · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

Global Score

48 vs 30

Hardware Fit

77 vs 66

Quality Score

35 vs 14

Hardware

qwen3.5:4b deepseek-coder-1.3…

MachineMac miniLENOVO 20BUS00700

CPUApple M4Intel Core™ i5-5300U

Cores104

RAM16 GB16 GB

GPUApple M4Intel(R) HD Graphics 5500

OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045

Archarm64x64

Power Modebalancedbalanced

Performance

qwen3.5:4b deepseek-coder-1.3…

Tokens/sec18.97.1

First chunk316 ms3448 ms

TTFT13.0 s3.4 s

Load time3.7 sN/A

Memory usage5.9 GB1.3 GB

Memory %37%9%

HW Fit Score Breakdown

qwen3.5:4b

Speed

43/50

TTFT

4/20

Memory

30/30

deepseek-coder-1.3b-ins…

Speed

24/50

TTFT

15/20

Memory

27/30

Quality

qwen3.5:4b

Reasoning

10/20

Coding

1/20

Instruction

4/20

Structured

3/15

Math

8/15

Multilingual

9/10

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

deepseek-coder-1.3b-ins…

Reasoning

0/20

Coding

3/20

Instruction

3/20

Structured

6/15

Math

0/15

Multilingual

2/10

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

View qwen3.5:4b details | View deepseek-coder-1.3… 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