Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

Qwen3-30B:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

Global Score
59 vs 91
Hardware Fit
65 vs 98
Quality Score
57 vs 88

Hardware

qwen3.5-9b-mlx Qwen3-30B:30b
MachineMac miniHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUApple M4NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores1020
RAM24 GB55 GB
GPUApple M4NVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.28000
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx Qwen3-30B:30b
Tokens/sec14.380.5
First chunk24 ms158 ms
TTFT13.4 s158 ms
Load time13.3 s21.8 s
Memory usage2.5 GB20.3 GB
Memory %10%37%

HW Fit Score Breakdown

qwen3.5-9b-mlx

Speed
32/50
TTFT
3/20
Memory
30/30

Qwen3-30B:30b

Speed
50/50
TTFT
20/20
Memory
28/30

Quality

qwen3.5-9b-mlx

Reasoning
10/20
Coding
17/20
Instruction
5/20
Structured
9/15
Math
11/15
Multilingual
5/10
Reasoning: Weak Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Adequate Multilingual: Adequate

Qwen3-30B:30b

Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5-9b-mlx details | View Qwen3-30B:30b 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