Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Global Score
62 vs 78
Hardware Fit
77 vs 59
Quality Score
55 vs 86

Hardware

google/gemma-4-e4b qwen2.5-coder:32b
MachineLENOVO 82JQNVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 7 5800HCortex-X925
Cores1620
RAM16 GB122 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUDevice 2e12
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance

Performance

google/gemma-4-e4b qwen2.5-coder:32b
Tokens/sec27.69.5
First chunk23 ms394 ms
TTFT480 ms395 ms
Load timeN/A72.1 s
Memory usage13.2 GB26.5 GB
Memory %83%22%

HW Fit Score Breakdown

google/gemma-4-e4b

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

qwen2.5-coder:32b

Speed
9/50
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

qwen2.5-coder:32b

Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View google/gemma-4-e4b details | View qwen2.5-coder:32b 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