Back to leaderboard

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

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

Hardware

qwen2.5-coder:32b google/gemma-4-e4b
MachineNVIDIA NVIDIA_DGX_SparkLENOVO 82JQ
CPUCortex-X925AMD Ryzen 7 5800H
Cores2016
RAM122 GB16 GB
GPUDevice 2e12NVIDIA GeForce RTX 3060 Laptop GPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 家庭版 中文版 10.0.26100
Archarm64x64
Power Modeperformancebalanced

Performance

qwen2.5-coder:32b google/gemma-4-e4b
Tokens/sec9.527.6
First chunk394 ms23 ms
TTFT395 ms480 ms
Load time72.1 sN/A
Memory usage26.5 GB13.2 GB
Memory %22%83%

HW Fit Score Breakdown

qwen2.5-coder:32b

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

google/gemma-4-e4b

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

Quality

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

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
View qwen2.5-coder:32b details | View google/gemma-4-e4b 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