Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Marginal

Oct 12, 2026 · AMD Ryzen 5 5500

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Excellent

Apr 28, 2026 · Intel Xeon® Gold 6230

Global Score
50 vs 80
Hardware Fit
93 vs 85
Quality Score
31 vs 78

Hardware

qwen3.5:4b qwen3:8b
MachineMicrosoft WSLHP HP Z8 G4 Workstation
CPUAMD Ryzen 5 5500Intel Xeon® Gold 6230
Cores1280
RAM8 GB252 GB
GPUIntegrated / UnknownTU104GL [Quadro RTX 5000]
OSUbuntu 26.04.1 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modeunknownlow-power

Performance

qwen3.5:4b qwen3:8b
Tokens/sec92.665.1
First chunk323 ms289 ms
TTFT2.8 s4.2 s
Load time9.0 s4.6 s
Memory usage2.9 GB5.6 GB
Memory %38%2%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
15/20
Memory
28/30

qwen3:8b

Speed
50/50
TTFT
5/20
Memory
30/30

Quality

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
0/20
Structured
0/15
Math
12/15
Multilingual
0/10
Reasoning: Strong Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor

qwen3:8b

Reasoning
17/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:4b details | View qwen3:8b 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