mistral:latest

llama · 7.2B · Q4_0

Good

Feb 28, 2026 · Apple M4 Pro

deepseek-r1:14b

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 1, 2026 · Apple M4

Global Score

76 vs 25

Hardware Fit

100 vs 46

Quality Score

60 vs 11

Hardware

mistral:latest deepseek-r1:14b

MachineMac MiniMacBook Air

CPUApple M4 ProApple M4

Cores1410

RAM64 GB32 GB

GPUApple M4 ProApple M4

OSmacOS 15.7.4macOS 26.3

Archarm64arm64

Power Modeunknownunknown

Performance

mistral:latest deepseek-r1:14b

Tokens/sec54.310.8

TTFT124 ms30.0 s

Load time0.0 s5.3 s

Memory usage9.9 GB16.5 GB

Memory %15%52%

HW Fit Score Breakdown

mistral:latest

Speed

40/40

TTFT

30/30

Memory

30/30

deepseek-r1:14b

Speed

16/40

TTFT

0/30

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-r1:14b

Reasoning

1/20

Coding

0/20

Instruction

2/20

Structured

1/15

Math

1/15

Multilingual

6/10

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

View mistral:latest details | View deepseek-r1:14b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running