deepseek-v2:16b

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

llama3.1:8b

llama · 8.0B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

Global Score

73 vs 69

Hardware Fit

100 vs 93

Quality Score

55 vs 53

Hardware

deepseek-v2:16b llama3.1:8b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

deepseek-v2:16b llama3.1:8b

Tokens/sec56.620.2

TTFT239 ms481 ms

Load time1.2 s3.4 s

Memory usage17.7 GB10.4 GB

Memory %55%33%

HW Fit Score Breakdown

deepseek-v2:16b

Speed

40/40

TTFT

30/30

Memory

30/30

llama3.1:8b

Speed

33/40

TTFT

30/30

Memory

30/30

Quality

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

llama3.1:8b

Reasoning

12/20

Coding

0/20

Instruction

14/20

Structured

13/15

Math

4/15

Multilingual

10/10

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

View deepseek-v2:16b details | View llama3.1:8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running