smollm2:135m

llama · 134.52M · F16

Marginal

Mar 2, 2026 · Apple M4

deepseek-v2:16b

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

49 vs 73

Hardware Fit

100 vs 100

Quality Score

15 vs 55

Hardware

smollm2:135m deepseek-v2:16b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

smollm2:135m deepseek-v2:16b

Tokens/sec241.056.6

TTFT39 ms239 ms

Load time0.4 s1.2 s

Memory usage0.6 GB17.7 GB

Memory %2%55%

HW Fit Score Breakdown

smollm2:135m

Speed

40/40

TTFT

30/30

Memory

30/30

deepseek-v2:16b

Speed

40/40

TTFT

30/30

Memory

30/30

Quality

smollm2:135m

Reasoning

4/20

Coding

1/20

Instruction

6/20

Structured

2/15

Math

1/15

Multilingual

1/10

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

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 smollm2:135m details | View deepseek-v2:16b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running