Back to leaderboard

qwen3-vl:8b

OLLAMA GGUF

qwen3vl · 8.8B · Q4_K_M

Good

Apr 28, 2026 · Intel Xeon® Gold 6230

qwen3.5:35b-a3b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
72 vs 59
Hardware Fit
89 vs 69
Quality Score
64 vs 54

Hardware

qwen3-vl:8b qwen3.5:35b-a3b
MachineHP HP Z8 G4 WorkstationMacBook Pro
CPUIntel Xeon® Gold 6230Apple M4 Pro
Cores8014
RAM252 GB48 GB
GPUTU104GL [Quadro RTX 5000]Apple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 26.3.1
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3-vl:8b qwen3.5:35b-a3b
Tokens/sec68.230.5
First chunk285 ms333 ms
TTFT2.0 s30.0 s
Load time42.4 s9.8 s
Memory usage7.1 GB25.1 GB
Memory %3%52%

HW Fit Score Breakdown

qwen3-vl:8b

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

qwen3.5:35b-a3b

Speed
45/50
TTFT
0/20
Memory
24/30

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

qwen3.5:35b-a3b

Reasoning
18/20
Coding
1/20
Instruction
7/20
Structured
6/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong
View qwen3-vl:8b details | View qwen3.5:35b-a3b 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