qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

deepseek-r1:1.5b

OLLAMA GGUF

qwen2 · 1.8B · Q4_K_M

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score

58 vs 37

Hardware Fit

82 vs 73

Quality Score

48 vs 22

Hardware

qwen3:14b deepseek-r1:1.5b

MachineMacBook ProLENOVO 20L7CTO1WW

CPUApple M1 MaxIntel Core™ i5-8350U

Cores108

RAM32 GB23 GB

GPUApple M1 MaxKaby Lake-R GT2 [UHD Graphics 620]

OSmacOS 26.3Fedora Linux 43

Archarm64x64

Power Modebalancedlow-power

Performance

qwen3:14b deepseek-r1:1.5b

Tokens/sec24.418.4

First chunk294 ms593 ms

TTFT7.9 s30.0 s

Load time3.7 s3.8 s

Memory usage13.8 GB1.0 GB

Memory %43%4%

HW Fit Score Breakdown

qwen3:14b

Speed

47/50

TTFT

5/20

Memory

30/30

deepseek-r1:1.5b

Speed

43/50

TTFT

0/20

Memory

30/30

Quality

qwen3:14b

Reasoning

13/20

Coding

6/20

Instruction

10/20

Structured

9/15

Math

2/15

Multilingual

8/10

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

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

View qwen3:14b details | View deepseek-r1:1.5b 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