Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

Global Score
29 vs 77
Hardware Fit
86 vs 75
Quality Score
4 vs 78

Hardware

qwen3:4b qwen3.5:9b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperASUS
CPUCortex-A78AEIntel Gen Intel® Core™ i7-13700K
Cores624
RAM7 GB64 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 3070
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown

Performance

qwen3:4b qwen3.5:9b
Tokens/sec17.930.5
First chunk1010 ms291 ms
TTFT6.4 s291 ms
Load time9.5 s4.8 s
Memory usage3.0 GB8.8 GB
Memory %40%14%

HW Fit Score Breakdown

qwen3:4b

Speed
50/50
TTFT
8/20
Memory
28/30

qwen3.5:9b

Speed
34/50
TTFT
20/20
Memory
21/30

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

qwen3.5:9b

Reasoning
14/20
Coding
15/20
Instruction
14/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3:4b details | View qwen3.5:9b 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