GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

thesreedath/slm-500m-raft-dpo-GGUF overview

SLM 500M RAFT RLAIF closed book + RAG, GGUF On device offline quantizations of thesreedath/slm 500m raft dpo , our best 500M model with RAG standard Llama arch…

tfliteggufendpoints_compatibleregion:usconversational

Runs locally from ~325.9 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline

Repository Files & Downloads

3 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
slm-500m-raft-dpo-Q4_K_M.ggufGGUFQ4_K_M325.9 MBDownload
slm-500m-raft-dpo-Q8_0.ggufGGUFQ8_0526.0 MBDownload
slm-500m-raft-dpo-f16.ggufGGUFF16988.9 MBDownload

Model Details

Model IDthesreedath/slm-500m-raft-dpo-GGUF
Authorthesreedath
Pipeline
License
Base model
Last modified2026-07-24T11:14:12.000Z

Model README

SLM 500M - RAFT (RLAIF) closed-book + RAG, GGUF

On-device (offline) quantizations of thesreedath/slm-500m-raft-dpo, our best 500M model with RAG (standard Llama architecture, 24 layers, 1280 hidden, 32K vocab). Load with any llama.cpp runtime (Ollama, PocketPal AI, LM Studio, ChatterUI).

| file | size | use |

|---|---|---|

| Q4_K_M | ~341.7 MB | phone default |

| Q8_0 | ~551.5 MB | higher quality |

| F16 | ~1036.9 MB | laptop quality ceiling |

For RAG, prepend retrieved passages as context blocks before the question.

Run thesreedath/slm-500m-raft-dpo-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models