Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Nov 4, 2026 · Intel Core™ i7-9700

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
29 vs 82
Hardware Fit
84 vs 81
Quality Score
6 vs 82

Hardware

qwen3:4b qwen3.5:9b
MachineVMware, Inc. VMware Virtual PlatformAZW GTR Pro
CPUIntel Core™ i7-9700AMD RYZEN AI MAX+ 395
Cores432
RAM16 GB125 GB
GPUIntegrated / UnknownAMD Radeon 8060S
OSUbuntu 24.04.5 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modeunknownperformance

Performance

qwen3:4b qwen3.5:9b
Tokens/sec10.430.8
First chunk857 ms195 ms
TTFT857 ms195 ms
Load time41.0 s5.2 s
Memory usage3.0 GB18.8 GB
Memory %19%15%

HW Fit Score Breakdown

qwen3:4b

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

qwen3.5:9b

Speed
31/50
TTFT
20/20
Memory
30/30

Quality

qwen3:4b

Reasoning
0/20
Coding
2/20
Instruction
2/20
Structured
0/15
Math
1/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong 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