Back to leaderboard

Gemma4-26B:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Excellent

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

llama3.3:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-X925

Global Score
91 vs 73
Hardware Fit
93 vs 51
Quality Score
90 vs 83

Hardware

Gemma4-26B:26b llama3.3:70b
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxNVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorCortex-X925
Cores3220
RAM31 GB122 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPUDevice 2e12
OSMicrosoft Windows 11 Home 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance

Performance

Gemma4-26B:26b llama3.3:70b
Tokens/sec40.54.6
First chunk727 ms560 ms
TTFT727 ms560 ms
Load time25.3 s13.8 s
Memory usage17.0 GB49.5 GB
Memory %55%41%

HW Fit Score Breakdown

Gemma4-26B:26b

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

llama3.3:70b

Speed
4/50
TTFT
20/20
Memory
27/30

Quality

Gemma4-26B:26b

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

llama3.3:70b

Reasoning
17/20
Coding
18/20
Instruction
12/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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