Back to leaderboard

hf.co/empero-ai/Qwen3.8-4B-Distill-GGUF:Q4_K_M

OLLAMA GGUF

qwen35 · 4.33B · unknown

Good

Aug 28, 2026 · Apple M4

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

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

Global Score
66 vs 85
Hardware Fit
100 vs 78
Quality Score
52 vs 88

Hardware

hf.co/empero-ai/Qw… Kimi-48B:48B
MachineMacBook ProHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUApple M4AMD Ryzen 9 9955HX3D 16-Core Processor
Cores1032
RAM16 GB31 GB
GPUApple M4AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSmacOS 26.6.1Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

hf.co/empero-ai/Qw… Kimi-48B:48B
Tokens/sec26.542.3
First chunk447 ms718 ms
TTFT447 ms718 ms
Load time3.3 s28.5 s
Memory usage4.8 GB25.8 GB
Memory %30%83%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

Kimi-48B:48B

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

Quality

hf.co/empero-ai/Qwen3.8…

Reasoning
18/20
Coding
14/20
Instruction
4/20
Structured
1/15
Math
15/15
Multilingual
0/10
Reasoning: Strong Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor

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