codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

Global Score

67 vs 32

Hardware Fit

67 vs 98

Quality Score

67 vs 4

Hardware

codestral:22b qwen3:4b

MachineNVIDIA NVIDIA_DGX_SparkNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super

CPUCortex-X925Cortex-A78AE

Cores206

RAM122 GB7 GB

GPUDevice 2e12Integrated / Unknown

OSUbuntu 24.04.4 LTSUbuntu 22.04.5 LTS

Archarm64arm64

Power Modeperformancebalanced

Performance

codestral:22b qwen3:4b

Tokens/sec17.217.9

First chunk129 ms950 ms

TTFT129 ms950 ms

Load time11.6 s9.7 s

Memory usage18.9 GB3.0 GB

Memory %16%40%

HW Fit Score Breakdown

codestral:22b

Speed

17/50

TTFT

20/20

Memory

30/30

qwen3:4b

Speed

50/50

TTFT

20/20

Memory

28/30

Quality

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

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

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