stablelm2:1.6b

stablelm · 2B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

qwen3.5:0.8b

qwen35 · 873.44M · Q8_0

Good

Mar 2, 2026 · Apple M4

Global Score

45 vs 65

Hardware Fit

100 vs 99

Quality Score

22 vs 51

Hardware

stablelm2:1.6b qwen3.5:0.8b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

stablelm2:1.6b qwen3.5:0.8b

Tokens/sec93.848.2

TTFT94 ms195 ms

Load time0.4 s1.0 s

Memory usage1.1 GB2.5 GB

Memory %3%8%

HW Fit Score Breakdown

stablelm2:1.6b

Speed

40/40

TTFT

30/30

Memory

30/30

qwen3.5:0.8b

Speed

40/40

TTFT

30/30

Memory

29/30

Quality

stablelm2:1.6b

Reasoning

4/20

Coding

7/20

Instruction

6/20

Structured

1/15

Math

2/15

Multilingual

2/10

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

qwen3.5:0.8b

Reasoning

9/20

Coding

6/20

Instruction

11/20

Structured

13/15

Math

5/15

Multilingual

7/10

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

View stablelm2:1.6b details | View qwen3.5:0.8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running