Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor

Global Score
53 vs 85
Hardware Fit
82 vs 78
Quality Score
41 vs 88

Hardware

qwen3.5:4b-mlx Kimi-48B:48B
MachineMac miniHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUApple M2AMD Ryzen 9 9955HX3D 16-Core Processor
Cores832
RAM8 GB31 GB
GPUApple M2AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSmacOS 26.5.2Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx Kimi-48B:48B
Tokens/sec24.743.0
First chunk302 ms700 ms
TTFT7.4 s700 ms
Load time3.2 s29.4 s
Memory usage3.8 GB25.8 GB
Memory %47%83%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

Kimi-48B:48B

Speed
50/50
TTFT
20/20
Memory
8/30

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong

Kimi-48B:48B

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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