qwen3-vl:30b

OLLAMA GGUF

qwen3vlmoe · 31.1B · Q4_K_M

Excellent

Mar 5, 2026 · Intel Core™ Ultra 9 285K

deepseek-r1-distill-qwen-14b-mlx

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

Global Score

80 vs 36

Hardware Fit

98 vs 53

Quality Score

72 vs 28

Hardware

qwen3-vl:30b deepseek-r1-distil…

MachineASUSMac mini

CPUIntel Core™ Ultra 9 285KApple M4

Cores2410

RAM47 GB24 GB

GPUNVIDIA GeForce RTX 5090, Intel(R) GraphicsApple M4

OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3

Archx64arm64

Power Modebalancedbalanced

Performance

qwen3-vl:30b deepseek-r1-distil…

Tokens/sec208.910.3

First chunk102 ms27 ms

TTFT684 ms20.7 s

Load time0.1 s15.4 s

Memory usage22.0 GB1.0 GB

Memory %47%4%

HW Fit Score Breakdown

qwen3-vl:30b

Speed

50/50

TTFT

20/20

Memory

28/30

deepseek-r1-distill-qwe…

Speed

23/50

TTFT

0/20

Memory

30/30

Quality

qwen3-vl:30b

Reasoning

14/20

Coding

6/20

Instruction

17/20

Structured

12/15

Math

13/15

Multilingual

10/10

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

deepseek-r1-distill-qwe…

Reasoning

3/20

Coding

6/20

Instruction

6/20

Structured

3/15

Math

2/15

Multilingual

8/10

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

View qwen3-vl:30b details | View deepseek-r1-distil… 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