Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Marginal

Oct 12, 2026 · AMD Ryzen 5 5500

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Excellent

Aug 22, 2026 · Intel Xeon® E5-2637 v3

Global Score
50 vs 90
Hardware Fit
93 vs 98
Quality Score
31 vs 86

Hardware

qwen3.5:4b qwen3.5:35b-a3b-q4…
MachineMicrosoft WSLDell Inc. Precision Tower 7910
CPUAMD Ryzen 5 5500Intel Xeon® E5-2637 v3
Cores1216
RAM8 GB96 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSUbuntu 26.04.1 LTSMicrosoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modeunknownbalanced

Performance

qwen3.5:4b qwen3.5:35b-a3b-q4…
Tokens/sec92.647.1
First chunk323 ms1063 ms
TTFT2.8 s1.1 s
Load time9.0 s17.3 s
Memory usage2.9 GB22.9 GB
Memory %38%24%

HW Fit Score Breakdown

qwen3.5:4b

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

qwen3.5:35b-a3b-q4_K_M

Speed
50/50
TTFT
18/20
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

qwen3.5:35b-a3b-q4_K_M

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:4b details | View qwen3.5:35b-a3b-q4… 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