Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

mistral:latest

OLLAMA GGUF

llama · 7.2B · Q4_K_M

Good

May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor

Global Score
62 vs 73
Hardware Fit
77 vs 100
Quality Score
55 vs 62

Hardware

google/gemma-4-e4b mistral:latest
MachineLENOVO 82JQMicro-Star International Co., Ltd. MS-7B79
CPUAMD Ryzen 7 5800HAMD Ryzen 5 2600X Six-Core Processor
Cores1612
RAM16 GB16 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUNVIDIA GeForce GTX 1080
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Microsoft Windows 11 Famille 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b mistral:latest
Tokens/sec27.631.7
First chunk23 ms102 ms
TTFT480 ms102 ms
Load timeN/A14.3 s
Memory usage13.2 GB4.8 GB
Memory %83%30%

HW Fit Score Breakdown

google/gemma-4-e4b

Speed
48/50
TTFT
20/20
Memory
9/30

mistral:latest

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

Quality

google/gemma-4-e4b

Reasoning
18/20
Coding
17/20
Instruction
5/20
Structured
3/15
Math
11/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor

mistral:latest

Reasoning
8/20
Coding
13/20
Instruction
16/20
Structured
12/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View google/gemma-4-e4b details | View mistral:latest 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