Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

Global Score
32 vs 61
Hardware Fit
98 vs 69
Quality Score
4 vs 58

Hardware

qwen3:4b qwen3.5:4b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperGigabyte Technology Co., Ltd. H170M-D3H
CPUCortex-A78AEIntel Core™ i5-6500
Cores64
RAM7 GB16 GB
GPUIntegrated / UnknownGP104 [GeForce GTX 1070]
OSUbuntu 22.04.5 LTSUbuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3:4b qwen3.5:4b
Tokens/sec17.935.7
First chunk950 ms438 ms
TTFT950 ms5.1 s
Load time9.7 s40.1 s
Memory usage3.0 GB5.5 GB
Memory %40%35%

HW Fit Score Breakdown

qwen3:4b

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

qwen3.5:4b

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

Quality

qwen3:4b

Reasoning
4/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

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
View qwen3:4b details | View qwen3.5:4b 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