Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

qwen3-vl:2b

OLLAMA GGUF

qwen3vl · 2.1B · Q4_K_M

Good

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
61 vs 62
Hardware Fit
69 vs 99
Quality Score
58 vs 46

Hardware

qwen3.5:4b qwen3-vl:2b
MachineGigabyte Technology Co., Ltd. H170M-D3HAZW GTR Pro
CPUIntel Core™ i5-6500AMD RYZEN AI MAX+ 395
Cores432
RAM16 GB125 GB
GPUGP104 [GeForce GTX 1070]AMD Radeon 8060S
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modelow-powerlow-power

Performance

qwen3.5:4b qwen3-vl:2b
Tokens/sec35.7127.4
First chunk438 ms101 ms
TTFT5.1 s630 ms
Load time40.1 s5.9 s
Memory usage5.5 GB33.2 GB
Memory %35%27%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
11/20
Memory
8/30

qwen3-vl:2b

Speed
50/50
TTFT
19/20
Memory
30/30

Quality

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

qwen3-vl:2b

Reasoning
7/20
Coding
0/20
Instruction
11/20
Structured
7/15
Math
13/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Strong Multilingual: Strong

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