deepseek-v2:16b

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

mistral-nemo:12b

llama · 12.2B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

73 vs 73

Hardware Fit

100 vs 86

Quality Score

55 vs 65

Hardware

deepseek-v2:16b mistral-nemo:12b

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 mistral-nemo:12b

Tokens/sec56.614.6

TTFT239 ms371 ms

Load time1.2 s1.0 s

Memory usage17.7 GB13.3 GB

Memory %55%42%

HW Fit Score Breakdown

deepseek-v2:16b

Speed

40/40

TTFT

30/30

Memory

30/30

mistral-nemo:12b

Speed

26/40

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

mistral-nemo:12b

Reasoning

12/20

Coding

13/20

Instruction

11/20

Structured

15/15

Math

4/15

Multilingual

10/10

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

View deepseek-v2:16b details | View mistral-nemo:12b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running