Back to leaderboard

qwen3-vl:8b

OLLAMA GGUF

qwen3vl · 8.8B · Q4_K_M

Good

Apr 28, 2026 · Intel Xeon® Gold 6230

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Global Score
72 vs 65
Hardware Fit
89 vs 88
Quality Score
64 vs 55

Hardware

qwen3-vl:8b qwen3.5-2b-mlx
MachineHP HP Z8 G4 WorkstationMac mini
CPUIntel Xeon® Gold 6230Apple M4 Pro
Cores8014
RAM252 GB64 GB
GPUTU104GL [Quadro RTX 5000]Apple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 15.7.4
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3-vl:8b qwen3.5-2b-mlx
Tokens/sec68.248.9
First chunk285 ms4208 ms
TTFT2.0 s4.2 s
Load time42.4 sN/A
Memory usage7.1 GB1.6 GB
Memory %3%3%

HW Fit Score Breakdown

qwen3-vl:8b

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

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
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

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3-vl:8b details | View qwen3.5-2b-mlx 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