Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Nov 4, 2026 · Intel Core™ i7-9700

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Excellent

Apr 28, 2026 · Intel Xeon® Gold 6230

Global Score
29 vs 80
Hardware Fit
84 vs 85
Quality Score
6 vs 78

Hardware

qwen3:4b qwen3:8b
MachineVMware, Inc. VMware Virtual PlatformHP HP Z8 G4 Workstation
CPUIntel Core™ i7-9700Intel Xeon® Gold 6230
Cores480
RAM16 GB252 GB
GPUIntegrated / UnknownTU104GL [Quadro RTX 5000]
OSUbuntu 24.04.5 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modeunknownlow-power

Performance

qwen3:4b qwen3:8b
Tokens/sec10.465.1
First chunk857 ms289 ms
TTFT857 ms4.2 s
Load time41.0 s4.6 s
Memory usage3.0 GB5.6 GB
Memory %19%2%

HW Fit Score Breakdown

qwen3:4b

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

qwen3:8b

Speed
50/50
TTFT
5/20
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

qwen3:8b

Reasoning
17/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3:4b details | View qwen3:8b 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