deepseek-r1:1.5b

OLLAMA GGUF

qwen2 · 1.8B · Q4_K_M

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Good

Aug 25, 2026 · Apple M1 Pro

Global Score

37 vs 68

Hardware Fit

73 vs 91

Quality Score

22 vs 58

Hardware

deepseek-r1:1.5b qwen3.5:4b-mlx

MachineLENOVO 20L7CTO1WWMacBook Pro

CPUIntel Core™ i5-8350UApple M1 Pro

Cores810

RAM23 GB16 GB

GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M1 Pro

OSFedora Linux 43macOS 26.6.2

Archx64arm64

Power Modelow-powerbalanced

Performance

deepseek-r1:1.5b qwen3.5:4b-mlx

Tokens/sec18.442.2

First chunk593 ms201 ms

TTFT30.0 s4.4 s

Load time3.8 s0.0 s

Memory usage1.0 GB3.8 GB

Memory %4%24%

HW Fit Score Breakdown

deepseek-r1:1.5b

Speed

43/50

TTFT

0/20

Memory

30/30

qwen3.5:4b-mlx

Speed

50/50

TTFT

11/20

Memory

30/30

Quality

deepseek-r1:1.5b

Reasoning

4/20

Coding

0/20

Instruction

5/20

Structured

3/15

Math

7/15

Multilingual

3/10

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

qwen3.5:4b-mlx

Reasoning

16/20

Coding

2/20

Instruction

13/20

Structured

7/15

Math

11/15

Multilingual

9/10

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

View deepseek-r1:1.5b details | View qwen3.5:4b-mlx 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