qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

Global Score

32 vs 67

Hardware Fit

98 vs 67

Quality Score

4 vs 67

Hardware

qwen3:4b codestral:22b

MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperNVIDIA NVIDIA_DGX_Spark

CPUCortex-A78AECortex-X925

Cores620

RAM7 GB122 GB

GPUIntegrated / UnknownDevice 2e12

OSUbuntu 22.04.5 LTSUbuntu 24.04.4 LTS

Archarm64arm64

Power Modebalancedperformance

Performance

qwen3:4b codestral:22b

Tokens/sec17.917.2

First chunk950 ms129 ms

TTFT950 ms129 ms

Load time9.7 s11.6 s

Memory usage3.0 GB18.9 GB

Memory %40%16%

HW Fit Score Breakdown

qwen3:4b

Speed

50/50

TTFT

20/20

Memory

28/30

codestral:22b

Speed

17/50

TTFT

20/20

Memory

30/30

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

codestral:22b

Reasoning

11/20

Coding

17/20

Instruction

9/20

Structured

14/15

Math

6/15

Multilingual

10/10

Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong

View qwen3:4b details | View codestral:22b 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