license: apache-2.0
base_model:
- brishen/iron-huihui-qwen3.5-2b-abliterated-npu2
base_model_relation: quantized
quantized_by: Atomic-Germ
pipeline_tag: image-text-to-text
oflm-family: qwen3.5
tags: - transformers
- safetensors
- qwen3_5
- image-text-to-text
- conversational
- base_model:Qwen/Qwen3.5-2B-Base
- base_model:finetune:brishen/iron-huihui-qwen3.5-2b-abliterated-npu2
- license:apache-2.0
- eval-results
- endpoints_compatible
- deploy:sagemaker
- deploy:azure
- region:us
- oflm
- openflowlm
- npu2
- q4nx
brishen--iron-huihui-qwen3.5-2b-abliterated-npu2
OpenFlowLM Q4NX conversion of brishen/iron-huihui-qwen3.5-2b-abliterated-npu2 for AMD XDNA NPU inference.
This repository contains a quantized Q4NX port of the model, compiled for the OpenFlowLM (OFLM) runtime. It is not a GGUF file.
| Item | Value |
|---|---|
| Source model | brishen/iron-huihui-qwen3.5-2b-abliterated-npu2 |
| Weights | model.q4nx (2.29 GB) |
| Modality | language |
| OFLM version | 0.1.0 |
| Converted | 2026-09-30 |
Install and run
This repository works with oflm add, a small installer that copies the model
into the OpenFlowLM user directory and registers the tag. It never
modifies the system OpenFlowLM install.
Files
| File | Description |
|---|---|
model.q4nx |
Quantized weights (Q8_0 / Q4_1 / BF16) |
config.json |
OFLM runtime configuration |
tokenizer.json |
Tokenizer vocabulary |
tokenizer_config.json |
Tokenizer configuration |
chat_template.jinja |
Chat template |
Source model card
See the original model card: brishen/iron-huihui-qwen3.5-2b-abliterated-npu2