Back to leaderboard

qwen3-vl:8b

OLLAMA GGUF

qwen3vl · 8.8B · Q4_K_M

Good

Apr 28, 2026 · Intel Xeon® Gold 6230

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
72 vs 61
Hardware Fit
89 vs 85
Quality Score
64 vs 51

Hardware

qwen3-vl:8b qwen3:0.6b
MachineHP HP Z8 G4 WorkstationLENOVO 20L7CTO1WW
CPUIntel Xeon® Gold 6230Intel Core™ i5-8350U
Cores808
RAM252 GB23 GB
GPUTU104GL [Quadro RTX 5000]Kaby Lake-R GT2 [UHD Graphics 620]
OSUbuntu 24.04.4 LTSFedora Linux 43
Archx64x64
Power Modelow-powerlow-power

Performance

qwen3-vl:8b qwen3:0.6b
Tokens/sec68.227.0
First chunk285 ms597 ms
TTFT2.0 s8.7 s
Load time42.4 s1.8 s
Memory usage7.1 GB0.9 GB
Memory %3%4%

HW Fit Score Breakdown

qwen3-vl:8b

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

qwen3:0.6b

Speed
50/50
TTFT
5/20
Memory
30/30

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

qwen3:0.6b

Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate

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