Back to leaderboard

qwen3-vl:8b

OLLAMA GGUF

qwen3vl · 8.8B · Q4_K_M

Good

Apr 28, 2026 · Intel Xeon® Gold 6230

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

Global Score
72 vs 61
Hardware Fit
89 vs 69
Quality Score
64 vs 58

Hardware

qwen3-vl:8b qwen3.5:4b
MachineHP HP Z8 G4 WorkstationGigabyte Technology Co., Ltd. H170M-D3H
CPUIntel Xeon® Gold 6230Intel Core™ i5-6500
Cores804
RAM252 GB16 GB
GPUTU104GL [Quadro RTX 5000]GP104 [GeForce GTX 1070]
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modelow-powerlow-power

Performance

qwen3-vl:8b qwen3.5:4b
Tokens/sec68.235.7
First chunk285 ms438 ms
TTFT2.0 s5.1 s
Load time42.4 s40.1 s
Memory usage7.1 GB5.5 GB
Memory %3%35%

HW Fit Score Breakdown

qwen3-vl:8b

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

qwen3.5:4b

Speed
50/50
TTFT
11/20
Memory
8/30

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

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

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