Downloads · 30 days
7
16% of all-time downloads
SmolVLM-256M-Instruct-HQQ-INT4-v2
Azaz666/SmolVLM-256M-Instruct-HQQ-INT4-v2
SmolVLM-256M-Instruct-HQQ-INT4-v2 is a machine learning model from Azaz666. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is a HQQ (4-bit) quantized version of HuggingFaceTB/SmolVLM-256M-Instruct.
All-time downloads
43
Public
Repo size
362 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt362 MB · 99%
At a glance
- License
- apache-2.0
- Model type
- idefics3
- Access
- Public
- Created
- Apr 27, 2026
- Updated
- Apr 27, 2026
- SHA
- 72a2ed66
Base models
Model card
From the Hugging Face model README
HuggingFaceTB__SmolVLM-256M-Instruct__hqq_int4
This is a HQQ (4-bit) quantized version of HuggingFaceTB/SmolVLM-256M-Instruct.
Quantization Details
- Method: HQQ
- Bits: 4
- Base model: HuggingFaceTB/SmolVLM-256M-Instruct
- Group size: 64
- FP16 modules: vision_model, vision_tower, visual, connector, multi_modal_projector, mlp1, lm_head, embed_tokens, patch_embed
- Calibration: none (HQQ is calibration-free)
- Backend: hqq.core.quantize.HQQLinear
Usage
from transformers import AutoProcessor, AutoModelForImageTextToText
import torch
model = AutoModelForImageTextToText.from_pretrained(
"{REPO_ID}",
torch_dtype=torch.float16,
device_map="auto",
trust_remote_code=True,
)
processor = AutoProcessor.from_pretrained("{REPO_ID}", trust_remote_code=True)
Replace {REPO_ID} with the repo ID of this model.
Original Model
See HuggingFaceTB/SmolVLM-256M-Instruct for the original FP16 model.
- Type
- idefics3
- License
- apache-2.0
- Created
- Apr 27, 2026
- Updated
- Apr 27, 2026