Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Nov 4, 2026 · Intel Core™ i7-9700

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score
29 vs 74
Hardware Fit
84 vs 99
Quality Score
6 vs 63

Hardware

qwen3:4b llama3.2:3b
MachineVMware, Inc. VMware Virtual PlatformNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ i7-9700Cortex-A78AE
Cores46
RAM16 GB7 GB
GPUIntegrated / UnknownIntegrated / Unknown
OSUbuntu 24.04.5 LTSUbuntu 22.04.5 LTS
Archx64arm64
Power Modeunknownbalanced

Performance

qwen3:4b llama3.2:3b
Tokens/sec10.421.1
First chunk857 ms1032 ms
TTFT857 ms1.0 s
Load time41.0 s8.4 s
Memory usage3.0 GB2.4 GB
Memory %19%32%

HW Fit Score Breakdown

qwen3:4b

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

llama3.2:3b

Speed
50/50
TTFT
20/20
Memory
29/30

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

llama3.2:3b

Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3:4b details | View llama3.2:3b 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