qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Marginal

Mar 2, 2026 · Apple M4

falcon3-1b-instruct

LM-STUDIO MLX

llama · 1B · 3bit

Marginal

Mar 4, 2026 · Apple M4

Global Score

47 vs 54

Hardware Fit

67 vs 100

Quality Score

38 vs 34

Hardware

qwen3:8b falcon3-1b-instruct

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3:8b falcon3-1b-instruct

Tokens/sec18.7121.8

First chunkN/A176 ms

TTFT12.1 s176 ms

Load time1.2 sN/A

Memory usage9.5 GB0.7 GB

Memory %30%2%

HW Fit Score Breakdown

qwen3:8b

Speed

31/50

TTFT

6/20

Memory

30/30

falcon3-1b-instruct

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

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

falcon3-1b-instruct

Reasoning

7/20

Coding

1/20

Instruction

12/20

Structured

7/15

Math

2/15

Multilingual

5/10

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

View qwen3:8b details | View falcon3-1b-instruct 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