Back to leaderboard

qwen2.5-coder:0.5b

OLLAMA GGUF

qwen2 · 494.03M · Q4_K_M

Marginal

Nov 13, 2026 · Intel Core™ i5-4590T

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Nov 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score
59 vs 80
Hardware Fit
100 vs 83
Quality Score
41 vs 79

Hardware

qwen2.5-coder:0.5b google/gemma-4-e4b
MachineFUJITSU ESPRIMO Q920GMKtec EVO-X3
CPUIntel Core™ i5-4590TAMD RYZEN AI MAX+ 395
Cores432
RAM16 GB120 GB
GPUIntel(R) HD Graphics 4600, Microsoft Remote Display AdapterAMD Radeon(TM) 8060S Graphics
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modebalancedbalanced

Performance

qwen2.5-coder:0.5b google/gemma-4-e4b
Tokens/sec43.746.5
First chunk290 ms14 ms
TTFT290 ms1.9 s
Load time1.4 s7.6 s
Memory usage0.9 GB0.0 GB
Memory %6%0%

HW Fit Score Breakdown

qwen2.5-coder:0.5b

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

google/gemma-4-e4b

Speed
43/50
TTFT
10/20
Memory
30/30

Quality

qwen2.5-coder:0.5b

Reasoning
7/20
Coding
8/20
Instruction
10/20
Structured
10/15
Math
2/15
Multilingual
4/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak

google/gemma-4-e4b

Reasoning
14/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen2.5-coder:0.5b 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