qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

text-embedding-nomic-embed-text-v1.5

LM-STUDIO GGUF

nomic-bert · Q4_K_M

Marginal

Mar 3, 2026 · Apple M4

Global Score

89 vs 59

Hardware Fit

95 vs 94

Quality Score

87 vs 44

Hardware

qwen/qwen3-8b text-embedding-nom…

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 text-embedding-nom…

Tokens/sec33.445.3

First chunk257 ms2440 ms

TTFT257 ms2.4 s

Load timeN/AN/A

Memory usage4.3 GB0.0 GB

Memory %7%0%

HW Fit Score Breakdown

qwen/qwen3-8b

Speed

45/50

TTFT

20/20

Memory

30/30

text-embedding-nomic-em…

Speed

40/50

TTFT

25/20

Memory

29/30

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

text-embedding-nomic-em…

Reasoning

10/20

Coding

3/20

Instruction

11/20

Structured

12/15

Math

3/15

Multilingual

5/10

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

View qwen/qwen3-8b details | View text-embedding-nom… 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