qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

smollm2:135m

OLLAMA GGUF

llama · 134.52M · F16

Marginal

Mar 2, 2026 · Apple M4

Global Score

89 vs 41

Hardware Fit

95 vs 100

Quality Score

87 vs 15

Hardware

qwen/qwen3-8b smollm2:135m

MachineMac miniMacBook Air

CPUApple M4 ProApple M4

Cores1410

RAM64 GB32 GB

GPUApple M4 ProApple M4

OSmacOS 15.7.4macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen/qwen3-8b smollm2:135m

Tokens/sec33.4241.0

First chunk257 msN/A

TTFT257 ms39 ms

Load timeN/A0.4 s

Memory usage4.3 GB0.6 GB

Memory %7%2%

HW Fit Score Breakdown

qwen/qwen3-8b

Speed

45/50

TTFT

20/20

Memory

30/30

smollm2:135m

Speed

40/50

TTFT

30/20

Memory

30/30

Quality

qwen/qwen3-8b

Reasoning

19/20

Coding

14/20

Instruction

16/20

Structured

15/15

Math

13/15

Multilingual

10/10

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

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

View qwen/qwen3-8b details | View smollm2:135m 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