deepseek-r1:1.5b

OLLAMA GGUF

qwen2 · 1.8B · Q4_K_M

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score

37 vs 80

Hardware Fit

73 vs 77

Quality Score

22 vs 81

Hardware

deepseek-r1:1.5b qwen3.6:35b-mlx

MachineLENOVO 20L7CTO1WWMacBook Pro

CPUIntel Core™ i5-8350UApple M5 Max

Cores818

RAM23 GB48 GB

GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M5 Max

OSFedora Linux 43macOS 26.5.2

Archx64arm64

Power Modelow-powerbalanced

Performance

deepseek-r1:1.5b qwen3.6:35b-mlx

Tokens/sec18.4129.8

First chunk593 ms77 ms

TTFT30.0 s30.0 s

Load time3.8 s1.8 s

Memory usage1.0 GB19.7 GB

Memory %4%41%

HW Fit Score Breakdown

deepseek-r1:1.5b

Speed

43/50

TTFT

0/20

Memory

30/30

qwen3.6:35b-mlx

Speed

50/50

TTFT

0/20

Memory

27/30

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

qwen3.6:35b-mlx

Reasoning

19/20

Coding

9/20

Instruction

18/20

Structured

11/15

Math

14/15

Multilingual

10/10

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

View deepseek-r1:1.5b details | View qwen3.6:35b-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