Back to leaderboard

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

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

Global Score
91 vs 75
Hardware Fit
86 vs 50
Quality Score
93 vs 86

Hardware

gemma-4-26b-a4b-it… qwen2.5:72b
MachineASUSNVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorCortex-X925
Cores1620
RAM31 GB122 GB
GPUNVIDIA GeForce RTX 4090, RaphaelDevice 2e12
OScachyos rollingUbuntu 24.04.4 LTS
Archx64arm64
Power Modelow-powerperformance

Performance

gemma-4-26b-a4b-it… qwen2.5:72b
Tokens/sec167.84.4
First chunk18 ms529 ms
TTFT128 ms529 ms
Load timeN/A49.7 s
Memory usage20.9 GB54.0 GB
Memory %69%44%

HW Fit Score Breakdown

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

Speed
50/50
TTFT
20/20
Memory
16/30

qwen2.5:72b

Speed
4/50
TTFT
20/20
Memory
26/30

Quality

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

qwen2.5:72b

Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View gemma-4-26b-a4b-it… details | View qwen2.5:72b 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