gemma4:latest

gemma4 · 8.0B · Q4_K_M

THINKING MODEL

Micro-Star International Co., Ltd. MS-7E47 (AMD Ryzen 9 9950X 16-Core Processor)

125 GB · Microsoft Windows 11 Pro 10.0.26100

Tested on July 11, 2026 · Submitted by szargarpour

Top 15% Compare

Global Score

87 /100

Excellent

Hardware Fit

75/100

Quality

92/100

Get this model

🦙

Ollama

ollama pull gemma4:latest

View on Ollama Library

ollama.com/library/gemma4

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: Micro-Star International Co., Ltd. MS-7E47
CPU: AMD Ryzen 9 9950X 16-Core Processor
Cores: 32 total (32 perf)
Frequency: 4.3 GHz
RAM: 125 GB DDR5
GPU: AMD Radeon(TM) Graphics, NVIDIA GeForce RTX 4080 SUPER
OS: Microsoft Windows 11 Pro 10.0.26100
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 42.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±1.9
First chunk latency Delay before the first streamed chunk arrives from runtime: 472 ms
Time to first token How fast the model starts responding — lower is better: 3.8 s
Load time Time to load the model into memory before inference: 0.3 s
Memory usage RAM consumed during inference — percentage of total system memory: 12.3 GB (10%)
Total tokens Total number of tokens generated across all benchmark prompts: 1432
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~537

Score breakdown

Speed

40/50

Time to first token

5/20

Memory

30/30

Quality

Reasoning

19/20

Coding

18/20

Instruction following

15/20

Structured output

15/15

Math

15/15

Multilingual

10/10

Category levels

Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.31.2
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 1d00f8150517a79c41a1e8fb99777ae2cc7be95a0c664e70eb9552c15f17572b

Interpretation

Hardware fit: 75/100. Overall suitability: EXCELLENT (Global 87/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Bench Environment

CPU load: avg 45% (peak 52%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest