deepseek-r1:14b

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 2, 2026 · Apple M4

qwen3.5:0.8b

qwen35 · 873.44M · Q8_0

Good

Mar 2, 2026 · Apple M4

Global Score

22 vs 65

Hardware Fit

50 vs 99

Quality Score

10 vs 51

Hardware

deepseek-r1:14b qwen3.5:0.8b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

deepseek-r1:14b qwen3.5:0.8b

Tokens/sec11.448.2

TTFT30.0 s195 ms

Load time1.0 s1.0 s

Memory usage16.5 GB2.5 GB

Memory %52%8%

HW Fit Score Breakdown

deepseek-r1:14b

Speed

20/40

TTFT

0/30

Memory

30/30

qwen3.5:0.8b

Speed

40/40

TTFT

30/30

Memory

29/30

Quality

deepseek-r1:14b

Reasoning

1/20

Coding

3/20

Instruction

1/20

Structured

0/15

Math

0/15

Multilingual

5/10

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

qwen3.5:0.8b

Reasoning

9/20

Coding

6/20

Instruction

11/20

Structured

13/15

Math

5/15

Multilingual

7/10

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

View deepseek-r1:14b details | View qwen3.5:0.8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running