Back to leaderboard

qwen3-vl:4b-instruct

OLLAMA GGUF

qwen3vl · 4.4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

unsloth/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q3_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
83 vs 85
Hardware Fit
96 vs 79
Quality Score
78 vs 88

Hardware

qwen3-vl:4b-instruct unsloth/qwen3.6-35…
MachineMac StudioSystem manufacturer
CPUApple M2 MaxAMD Ryzen 7 5800X 8-Core Processor
Cores1216
RAM96 GB31 GB
GPUApple M2 MaxNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.1Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3-vl:4b-instruct unsloth/qwen3.6-35…
Tokens/sec90.623.5
First chunk159 ms54 ms
TTFT159 ms457 ms
Load time5.8 sN/A
Memory usage42.5 GB18.3 GB
Memory %44%59%

HW Fit Score Breakdown

qwen3-vl:4b-instruct

Speed
50/50
TTFT
20/20
Memory
26/30

unsloth/qwen3.6-35b-a3b

Speed
38/50
TTFT
20/20
Memory
21/30

Quality

qwen3-vl:4b-instruct

Reasoning
14/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

unsloth/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3-vl:4b-instruct details | View unsloth/qwen3.6-35… 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