mistral:latest

llama · 7.2B · Q4_0

Good

Feb 28, 2026 · Apple M4 Pro

deepseek-v2:16b

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

72 vs 69

Hardware Fit

100 vs 100

Quality Score

60 vs 55

Hardware

mistral:latest deepseek-v2:16b

MachineMac MiniMacBook Air

CPUApple M4 ProApple M4

Cores1410

RAM64 GB32 GB

GPUApple M4 ProApple M4

OSmacOS 15.7.4macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

mistral:latest deepseek-v2:16b

Tokens/sec54.356.6

TTFT124 ms239 ms

Load time0.0 s1.2 s

Memory usage9.9 GB17.7 GB

Memory %15%55%

HW Fit Score Breakdown

mistral:latest

Speed

40/40

TTFT

30/30

Memory

30/30

deepseek-v2:16b

Speed

40/40

TTFT

30/30

Memory

30/30

Quality

mistral:latest

Reasoning

8/20

Coding

15/20

Instruction

13/20

Structured

12/15

Math

3/15

Multilingual

9/10

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

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 mistral:latest details | View deepseek-v2:16b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running