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

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score

37 vs 62

Hardware Fit

73 vs 35

Quality Score

22 vs 73

Hardware

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

MachineLENOVO 20L7CTO1WWMac mini

CPUIntel Core™ i5-8350UApple M4 Pro

Cores814

RAM23 GB64 GB

GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M4 Pro

OSFedora Linux 43macOS 15.7.4

Archx64arm64

Power Modelow-powerbalanced

Performance

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

Tokens/sec18.40.0

First chunk593 ms5548 ms

TTFT30.0 s5.5 s

Load time3.8 sN/A

Memory usage1.0 GB2.9 GB

Memory %4%5%

HW Fit Score Breakdown

deepseek-r1:1.5b

Speed

43/50

TTFT

0/20

Memory

30/30

qwen3.5-4b-mlx

Speed

0/50

TTFT

6/20

Memory

29/30

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

17/20

Coding

17/20

Instruction

9/20

Structured

8/15

Math

13/15

Multilingual

9/10

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