Back to leaderboard

qwen3-vl:8b

OLLAMA GGUF

qwen3vl · 8.8B · Q4_K_M

Good

Apr 28, 2026 · Intel Xeon® Gold 6230

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

Global Score
72 vs 83
Hardware Fit
89 vs 96
Quality Score
64 vs 78

Hardware

qwen3-vl:8b google/gemma-4-e4b
MachineHP HP Z8 G4 WorkstationASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH
CPUIntel Xeon® Gold 6230AMD Ryzen 9 8940HX
Cores8032
RAM252 GB15 GB
GPUTU104GL [Quadro RTX 5000]NVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Home Single Language 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3-vl:8b google/gemma-4-e4b
Tokens/sec68.235.9
First chunk285 ms9 ms
TTFT2.0 s182 ms
Load time42.4 sN/A
Memory usage7.1 GB6.5 GB
Memory %3%43%

HW Fit Score Breakdown

qwen3-vl:8b

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

google/gemma-4-e4b

Speed
49/50
TTFT
20/20
Memory
27/30

Quality

qwen3-vl:8b

Reasoning
16/20
Coding
3/20
Instruction
10/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong Multilingual: Strong

google/gemma-4-e4b

Reasoning
14/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3-vl:8b 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