Back to leaderboard

qwen3-vl:8b

OLLAMA GGUF

qwen3vl · 8.8B · Q4_K_M

Good

Apr 28, 2026 · Intel Xeon® Gold 6230

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score
72 vs 74
Hardware Fit
89 vs 99
Quality Score
64 vs 63

Hardware

qwen3-vl:8b llama3.2:3b
MachineHP HP Z8 G4 WorkstationNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Xeon® Gold 6230Cortex-A78AE
Cores806
RAM252 GB7 GB
GPUTU104GL [Quadro RTX 5000]Integrated / Unknown
OSUbuntu 24.04.4 LTSUbuntu 22.04.5 LTS
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3-vl:8b llama3.2:3b
Tokens/sec68.221.1
First chunk285 ms1032 ms
TTFT2.0 s1.0 s
Load time42.4 s8.4 s
Memory usage7.1 GB2.4 GB
Memory %3%32%

HW Fit Score Breakdown

qwen3-vl:8b

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

llama3.2:3b

Speed
50/50
TTFT
20/20
Memory
29/30

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

llama3.2:3b

Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3-vl:8b details | View llama3.2:3b 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