Model Intelligence Sheet
jdluzen/DeepSeek-V4-Flash-0731-DSpark-Selective-GGUF overview
Additional quants, tested and working.
Runs locally from ~6.69 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| dspark-DeepSeek-V4-Flash-0731-Q2_K-dense.gguf | GGUF | Q2_K | 6.69 GB | Download |
Model Details
Model README
---
license: mit
base_model:
- Ralii/DeepSeek-V4-Flash-0731-DSpark-Selective-Q4_K_M-GGUF
---
Additional quants, tested and working.
Run jdluzen/DeepSeek-V4-Flash-0731-DSpark-Selective-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models