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

gemma-4-26b-a4b-it-qat

LM-STUDIO GGUF

gemma4 · 26B · Q4_K_XL

Excellent

Jul 7, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
66 vs 93
Hardware Fit
100 vs 93
Quality Score
52 vs 93

Hardware

hf.co/empero-ai/Qw… gemma-4-26b-a4b-it…
MachineMacBook ProASUS
CPUApple M4AMD Ryzen 7 7800X3D 8-Core Processor
Cores1016
RAM16 GB31 GB
GPUApple M4NVIDIA GeForce RTX 4090, Raphael
OSmacOS 26.6.1cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

hf.co/empero-ai/Qw… gemma-4-26b-a4b-it…
Tokens/sec26.5166.9
First chunk447 ms6 ms
TTFT447 ms113 ms
Load time3.3 sN/A
Memory usage4.8 GB16.2 GB
Memory %30%53%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

gemma-4-26b-a4b-it-qat

Speed
50/50
TTFT
20/20
Memory
23/30

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

gemma-4-26b-a4b-it-qat

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
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