Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Marginal

Oct 12, 2026 · AMD Ryzen 5 5500

qwen/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
50 vs 84
Hardware Fit
93 vs 79
Quality Score
31 vs 86

Hardware

qwen3.5:4b qwen/qwen3.6-35b-a3b
MachineMicrosoft WSLASUS
CPUAMD Ryzen 5 5500AMD Ryzen 7 7800X3D 8-Core Processor
Cores1216
RAM8 GB31 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 4090, Raphael
OSUbuntu 26.04.1 LTScachyos rolling
Archx64x64
Power Modeunknownlow-power

Performance

qwen3.5:4b qwen/qwen3.6-35b-a3b
Tokens/sec92.6115.8
First chunk323 ms9 ms
TTFT2.8 s310 ms
Load time9.0 sN/A
Memory usage2.9 GB25.3 GB
Memory %38%83%

HW Fit Score Breakdown

qwen3.5:4b

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

qwen/qwen3.6-35b-a3b

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

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

qwen/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:4b details | View qwen/qwen3.6-35b-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