Back to leaderboard

qwen3.5:9b-mlx

OLLAMA GGUF

nvfp4

Excellent

Aug 25, 2026 · Apple M1 Pro

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

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

Global Score
84 vs 90
Hardware Fit
94 vs 96
Quality Score
80 vs 88

Hardware

qwen3.5:9b-mlx Kimi-48B:48B
MachineMacBook ProHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUApple M1 ProNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores1020
RAM16 GB55 GB
GPUApple M1 ProNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.28000
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:9b-mlx Kimi-48B:48B
Tokens/sec25.062.7
First chunk357 ms397 ms
TTFT357 ms397 ms
Load time3.8 s16.8 s
Memory usage8.4 GB25.5 GB
Memory %52%47%

HW Fit Score Breakdown

qwen3.5:9b-mlx

Speed
50/50
TTFT
20/20
Memory
24/30

Kimi-48B:48B

Speed
50/50
TTFT
20/20
Memory
26/30

Quality

qwen3.5:9b-mlx

Reasoning
16/20
Coding
15/20
Instruction
14/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

Kimi-48B:48B

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:9b-mlx details | View Kimi-48B:48B 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