Back to leaderboard

qwen3-5-4b-q4-k-m

OLLAMA GGUF

llama · 4B · Q4_K_M

Excellent

Jul 9, 2026 · Intel Core™ i5-10400

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
83 vs 62
Hardware Fit
100 vs 77
Quality Score
76 vs 55

Hardware

qwen3-5-4b-q4-k-m google/gemma-4-e4b
MachineMac ProLENOVO 82JQ
CPUIntel Core™ i5-10400AMD Ryzen 7 5800H
Cores1216
RAM32 GB16 GB
GPUAMD Radeon RX 6700 XTNVIDIA GeForce RTX 3060 Laptop GPU
OSmacOS 26.5.1Microsoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

qwen3-5-4b-q4-k-m google/gemma-4-e4b
Tokens/sec62.727.6
First chunk278 ms23 ms
TTFT278 ms480 ms
Load time0.0 sN/A
Memory usage0.0 GB13.2 GB
Memory %0%83%

HW Fit Score Breakdown

qwen3-5-4b-q4-k-m

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

google/gemma-4-e4b

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

Quality

qwen3-5-4b-q4-k-m

Reasoning
14/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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 qwen3-5-4b-q4-k-m 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