Model Intelligence Sheet
yassinsiouda/merged-i1-GGUF overview
merged GGUF GGUF quants of a LoRA finetune of the base model , merged in bf16 before quantisation so only one lossy step is applied. Built with an importance m…
Runs locally from ~17.44 GB disk (24 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 |
|---|---|---|---|---|
| merged.i1-IQ4_XS.gguf | GGUF | IQ4_XS | 17.44 GB | Download |
Model Details
| Model ID | yassinsiouda/merged-i1-GGUF |
|---|---|
| Author | yassinsiouda |
| Pipeline | — |
| License | — |
| Base model | unknown |
| Last modified | 2026-08-01T19:35:53.000Z |
Model README
---
base_model: unknown
tags:
- gguf
- llama.cpp
- quantized
- imatrix
---
merged GGUF
GGUF quants of a LoRA finetune of the base model, merged in bf16 before
quantisation so only one lossy step is applied.
Built with an importance matrix calibrated on the finetuning data (agentic coding traces), hence the i1- prefix.
Files
| file | size |
|---|---|
| merged.i1-IQ4_XS.gguf | 18G |
Run
llama-cli -m merged.i1-IQ4_XS.gguf -ngl 99 -c 8192Run yassinsiouda/merged-i1-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models