yasserrmd/
Llama-4-Scout-17B-16E-Instruct:latest

551 8 months ago

tools

8 months ago

b6cf35b8f35b · 43GB ·

model
llama4
·
108B
·
Q2_K
params
{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"
template
{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|> {{- if .System }} {{ .System }

Readme

Llama-4-Scout-17B-16E-Instruct

Quantized version of Llama-4-Scout-17B-16E-Instruct, by Unsloth, optimized for instruction tasks and runs via Ollama.

Run

ollama run yasserrmd/Llama-4-Scout-17B-16E-Instruct

⚠️ Requires ~43 GiB system RAM even with Q2_K_XL quantization.

Notes

  • Format: Q2_K_XL (lightweight GGUF quant)
  • Good for Q&A, summaries, code, and chat
  • Built with Unsloth for efficient fine-tuning

Example

> Explain RAG in simple terms.