deepseek-r1:14b

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 2, 2026 · Apple M4

falcon:7b

falcon · 7B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score

26 vs 47

Hardware Fit

50 vs 98

Quality Score

10 vs 13

Hardware

deepseek-r1:14b falcon:7b

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 falcon:7b

Tokens/sec11.424.3

TTFT30.0 s256 ms

Load time1.0 s0.4 s

Memory usage16.5 GB4.0 GB

Memory %52%12%

HW Fit Score Breakdown

deepseek-r1:14b

Speed

20/40

TTFT

0/30

Memory

30/30

falcon:7b

Speed

38/40

TTFT

30/30

Memory

30/30

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

falcon:7b

Reasoning

0/20

Coding

0/20

Instruction

7/20

Structured

1/15

Math

1/15

Multilingual

4/10

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

View deepseek-r1:14b details | View falcon:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running