smollm2:1.7b

llama · 1.7B · Q8_0

Good

Mar 2, 2026 · Apple M4

qwen3:8b

qwen3 · 8.2B · Q4_K_M

Marginal

Mar 2, 2026 · Apple M4

Global Score

69 vs 50

Hardware Fit

100 vs 67

Quality Score

49 vs 38

Hardware

smollm2:1.7b qwen3:8b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

smollm2:1.7b qwen3:8b

Tokens/sec51.818.7

TTFT84 ms12.1 s

Load time0.4 s1.2 s

Memory usage3.7 GB9.5 GB

Memory %12%30%

HW Fit Score Breakdown

smollm2:1.7b

Speed

40/40

TTFT

30/30

Memory

30/30

qwen3:8b

Speed

31/40

TTFT

6/30

Memory

30/30

Quality

smollm2:1.7b

Reasoning

7/20

Coding

10/20

Instruction

12/20

Structured

13/15

Math

1/15

Multilingual

6/10

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

qwen3:8b

Reasoning

5/20

Coding

5/20

Instruction

4/20

Structured

12/15

Math

2/15

Multilingual

10/10

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

View smollm2:1.7b details | View qwen3:8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running