Downloads · 30 days
12
5% of all-time downloads
qwen3.5-9b-opus-agent-gptq-int8
malvavisc0/qwen3.5-9b-opus-agent-gptq-int8
qwen3.5-9b-opus-agent-gptq-int8 is a image-text-to-text model from malvavisc0. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
8-bit GPTQ quantized version of Qwen3.5 9B - Opus Agent.
All-time downloads
225
Public
Parameters
9.7B
26.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors13 GB · 100%
Parameter types
How the weights are stored.
I326.9B · 72%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.5 9B - Opus Agent (GPTQ Int8)
8-bit GPTQ quantized version of Qwen3.5 9B - Opus Agent.
Quantization: GPTQ 8-bit Framework: vLLM compatible Original model: Apache 2.0
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"malvavisc0/qwen3.5-9b-opus-agent-gptq-int8",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("malvavisc0/qwen3.5-9b-opus-agent-gptq-int8")
Benchmarks
Same benchmarks as the original model:
| Model | ARC | ARC/E | BoolQ |
|---|---|---|---|
| Qwen3.5-9B-Opus-Agent | 0.589 | 0.747 | 0.901 |
Notes
- Quantized with GPTQ 8-bit using gptqmodel 7.1.0
- Act-aware quantization enabled
- Compatible with vLLM for efficient inference
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_5
- License
- apache-2.0
- Languages
- en
- Created
- Jun 8, 2026
- Updated
- Jun 8, 2026