Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Good

Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor

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
78 vs 90
Hardware Fit
86 vs 82
Quality Score
74 vs 93

Hardware

qwen3:8b gemma-4-26b-a4b-it…
Machine—ASUS
CPUAMD Ryzen 9 3900X 12-Core ProcessorAMD Ryzen 7 7800X3D 8-Core Processor
Cores2416
RAM64 GB31 GB
GPUNVIDIA GeForce RTX 4060 TiNVIDIA GeForce RTX 4090, Raphael
OSMicrosoft Windows 11 Pro 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

qwen3:8b gemma-4-26b-a4b-it…
Tokens/sec48.5156.5
First chunk202 ms10 ms
TTFT4.3 s124 ms
Load time4.2 sN/A
Memory usage5.5 GB23.3 GB
Memory %9%76%

HW Fit Score Breakdown

qwen3:8b

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

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

Speed
50/50
TTFT
20/20
Memory
12/30

Quality

qwen3:8b

Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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
View qwen3:8b details | View gemma-4-26b-a4b-it… 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