Back to leaderboard

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

LM-STUDIO GGUF

gemma4 · 26B · Q4_0

Excellent

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Qwen3-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Excellent

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

Global Score
82 vs 87
Hardware Fit
56 vs 76
Quality Score
93 vs 91

Hardware

google/gemma-4-26b… Qwen3-80B:80B
MachineDocker ContainerHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUIntel Gen Intel® Core™ i9-11900HNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores1620
RAM15 GB55 GB
GPUTigerLake-H GT1 [UHD Graphics]NVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSUbuntu 26.04 LTSMicrosoft Windows 11 Pro 10.0.28000
Archx64arm64
Power Modeperformancebalanced

Performance

google/gemma-4-26b… Qwen3-80B:80B
Tokens/sec12.043.6
First chunk86 ms409 ms
TTFT2.8 s409 ms
Load time57.2 s80.3 s
Memory usage9.1 GB48.0 GB
Memory %59%88%

HW Fit Score Breakdown

google/gemma-4-26b-a4b-…

Speed
22/50
TTFT
14/20
Memory
20/30

Qwen3-80B:80B

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

Quality

google/gemma-4-26b-a4b-…

Reasoning
17/20
Coding
19/20
Instruction
20/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Qwen3-80B:80B

Reasoning
18/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View google/gemma-4-26b… details | View Qwen3-80B:80B 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