Back to leaderboard

qwen3-vl:8b

OLLAMA GGUF

qwen3vl · 8.8B · Q4_K_M

Good

Apr 28, 2026 · Intel Xeon® Gold 6230

slim-rpcache-ornith-1.0-9b

LM-STUDIO GGUF

qwen35 · 9B · BF16

Good

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
72 vs 79
Hardware Fit
89 vs 78
Quality Score
64 vs 79

Hardware

qwen3-vl:8b slim-rpcache-ornit…
MachineHP HP Z8 G4 WorkstationASUS
CPUIntel Xeon® Gold 6230AMD Ryzen 7 7800X3D 8-Core Processor
Cores8016
RAM252 GB31 GB
GPUTU104GL [Quadro RTX 5000]NVIDIA GeForce RTX 4090, Raphael
OSUbuntu 24.04.4 LTScachyos rolling
Archx64x64
Power Modelow-powerperformance

Performance

qwen3-vl:8b slim-rpcache-ornit…
Tokens/sec68.252.3
First chunk285 ms11 ms
TTFT2.0 s177 ms
Load time42.4 sN/A
Memory usage7.1 GB25.6 GB
Memory %3%84%

HW Fit Score Breakdown

qwen3-vl:8b

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

slim-rpcache-ornith-1.0…

Speed
50/50
TTFT
20/20
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

slim-rpcache-ornith-1.0…

Reasoning
16/20
Coding
16/20
Instruction
14/20
Structured
14/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3-vl:8b details | View slim-rpcache-ornit… 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