deepseek-v2:16b

OLLAMA GGUF

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

starling-lm:7b

OLLAMA GGUF

llama · 7B · Q4_0

Good

Mar 6, 2026 · Apple M4

Global Score

69 vs 65

Hardware Fit

100 vs 96

Quality Score

55 vs 52

Hardware

deepseek-v2:16b starling-lm:7b

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 starling-lm:7b

Tokens/sec56.623.8

First chunkN/A232 ms

TTFT239 ms232 ms

Load time1.2 s0.4 s

Memory usage17.7 GB5.3 GB

Memory %55%17%

HW Fit Score Breakdown

deepseek-v2:16b

Speed

40/50

TTFT

30/20

Memory

30/30

starling-lm:7b

Speed

46/50

TTFT

20/20

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

starling-lm:7b

Reasoning

10/20

Coding

13/20

Instruction

8/20

Structured

3/15

Math

9/15

Multilingual

9/10

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

View deepseek-v2:16b details | View starling-lm:7b details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest