llama3.2:1b

llama · 1.2B · Q8_0

Good

Mar 1, 2026 · Apple M4

deepseek-v2:16b

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

63 vs 73

Hardware Fit

100 vs 100

Quality Score

39 vs 55

Hardware

llama3.2:1b deepseek-v2:16b

Machine—MacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

llama3.2:1b deepseek-v2:16b

Tokens/sec28.256.6

TTFT199 ms239 ms

Load time1.8 s1.2 s

Memory usage4.3 GB17.7 GB

Memory %13%55%

HW Fit Score Breakdown

llama3.2:1b

Speed

40/40

TTFT

30/30

Memory

30/30

deepseek-v2:16b

Speed

40/40

TTFT

30/30

Memory

30/30

Quality

llama3.2:1b

Reasoning

4/20

Coding

0/20

Instruction

14/20

Structured

13/15

Math

1/15

Multilingual

7/10

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

deepseek-v2:16b

Reasoning

7/20

Coding

9/20

Instruction

13/20

Structured

10/15

Math

8/15

Multilingual

8/10

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

View llama3.2:1b details | View deepseek-v2:16b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running