SAVRN
Search Contact SAVRN

Open-weight model · Text generation

Qwen3.5-0.8-Cyber-GGUF

by Convergent Intelligence reaperdoesntknow/Qwen3.5-0.8-Cyber-GGUF

A compact Qwen3.5 0.8B repository with a practical GGUF quantization ladder for local inference. This card describes what is present in the repository.

Parameters
Context262,144
Weights4.2 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads6.8k

Model Card

By Convergent Intelligence, published under apache-2.0, revision 29303c8ed9fb.

A compact Qwen3.5 0.8B repository with a practical GGUF quantization ladder for local inference. This card describes what is present in the repository. The public files do not document the fine-tuning dataset or provide evaluation results, so the Cyber label should be read as the repository variant name—not as a verified capability claim. With a recent llama.cpp build: The repository includes a BF16 mmproj file and its configuration includes vision components. That establishes that a projector artifact is present; it does not establish that the end-to-end multimodal path was validated for this release. Verify image input locally before depending on it. - Local experimentation with a small…

Read Convergent Intelligence's full model card

Qwen3.5-0.8B Cyber — GGUF

A compact Qwen3.5 0.8B repository with a practical GGUF quantization ladder for local inference.

This card describes what is present in the repository. The public files do not document the fine-tuning dataset or provide evaluation results, so the Cyber label should be read as the repository variant name—not as a verified capability claim.

Repository contents

Variant Approximate size Practical use
BF16 1.52 GB Highest-fidelity reference build
Q8_0 812 MB High-quality local inference
Q6_K 630 MB Smaller high-quality option
Q4_K_M 529 MB Recommended size/quality starting point
Q2_K_L 484 MB Minimum footprint; expect greater quality loss
BF16-mmproj 207 MB Multimodal projector artifact; see caveat below

Run locally

With a recent llama.cpp build:

llama-cli \
  -hf reaperdoesntknow/Qwen3.5-0.8-Cyber-GGUF:Q4_K_M \
  --jinja

With Ollama:

ollama run hf.co/reaperdoesntknow/Qwen3.5-0.8-Cyber-GGUF:Q4_K_M

Multimodal note

The repository includes a BF16 mmproj file and its configuration includes vision components. That establishes that a projector artifact is present; it does not establish that the end-to-end multimodal path was validated for this release. Verify image input locally before depending on it.

Intended use

  • Local experimentation with a small Qwen3.5 model.
  • CPU- and memory-constrained prototyping.
  • Reproducible comparison of quantization levels.

Do not treat the model as an authoritative source for security, legal, medical, or operational decisions.

Evaluation status and limitations

  • No benchmark results or comparison baselines are published in this repository.
  • The fine-tuning dataset and training recipe are not documented in the public files reviewed for this card.
  • Quantization reduces memory use and can change output quality.
  • Model outputs may be incorrect, incomplete, biased, or unsafe.
  • The multimodal path requires independent verification.

Lineage and license

  • Base model: Qwen/Qwen3.5-0.8B
  • Format: GGUF
  • Conversion tooling recorded by the repository: Unsloth / llama.cpp
  • License: Apache-2.0

Part of the CIx cybersecurity model collection.

Configuration

Architecture
Qwen3_5ForConditionalGeneration
Context length (tokens)
262,144
Layers
24
Hidden size
1,024
Feed-forward size
3,584
Attention heads
8
Key/value heads
2
Head dimension
256
Vocabulary size
248,320
Model type
qwen3_5

Identity and Version

Repository
reaperdoesntknow/Qwen3.5-0.8-Cyber-GGUF
Publisher
Convergent Intelligence
Task
Text generation
Modality
Text
Library
gguf
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
29303c8ed9fbef2ee31787c45b6cbac610af9575
First published
2026-06-30
Last updated
2026-09-18

Files and Weights

9 files, 4.2 GB in total. The weights are 6 files totalling 4.2 GB in gguf.

Weights6 files · 4.2 GB
Configuration1 file · 2.7 KB
Documentation1 file · 2.7 KB
Repository1 file · 2.1 KB
Every file
FileTypeSizeSHA-256
Qwen_Qwen3.5-0.8B__project-qwen_1782801151.BF16-mmproj.ggufWeights207.3 MB b2d347d00a09
Qwen_Qwen3.5-0.8B__project-qwen_1782801151.BF16.ggufWeights1.5 GB 516ae0417263
Qwen_Qwen3.5-0.8B__project-qwen_1782801151.Q2_K_L.ggufWeights483.9 MB 714fc434c16c
Qwen_Qwen3.5-0.8B__project-qwen_1782801151.Q4_K_M.ggufWeights529.3 MB e75c26442048
Qwen_Qwen3.5-0.8B__project-qwen_1782801151.Q6_K.ggufWeights629.7 MB 2e78b5f8440a
Qwen_Qwen3.5-0.8B__project-qwen_1782801151.Q8_0.ggufWeights811.8 MB 42398496036b
config.jsonConfiguration2.7 KB
README.mdDocumentation2.7 KB
.gitattributesRepository2.1 KB

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
4.2 GB
Download from Convergent Intelligence

Released by Convergent Intelligence through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published4.2 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About Qwen3.5-0.8-Cyber-GGUF

Can I use Qwen3.5-0.8-Cyber-GGUF commercially?

Yes. Qwen3.5-0.8-Cyber-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

What is Qwen3.5-0.8-Cyber-GGUF's context length?

262,144 tokens, from the maximum position embeddings in its published configuration.

Similar Models

Fine-tune Qwen3 (14B) for free using our Google Colab notebook! - Read our Blog about Qwen3 support: unsloth.ai/blog/qwen3 - View the rest of our notebooks in our docs here. Qwen3-Coder is available in multiple sizes. Today, we're excited to introduce Qwen3-Coder-30B-A3B-Instruct. This streamlined model maintains impressive performance and efficiency, featuring the following key enhancements: - Significant Performance among open models on Agentic Coding, Agentic Browser-Use, and other foundational coding tasks. - Long-context Capabilities with native support for 256K tokens, extendable up to 1M tokens using Yarn, optimized for repository-scale understanding. - Agentic Coding supporting for…

Open weights apache-2.0 transformers

Model · Text generation

opt-125m

AI at Meta

OPT was first introduced in Open Pre-trained Transformer Language Models and first released in metaseq's repository on May 3rd 2022 by Meta AI. Disclaimer: The team releasing OPT wrote an official model card, which is available in Appendix D of the paper. Content from this model card has been written by the Hugging Face team. To quote the first two paragraphs of the official paper OPT was predominantly pretrained with English text, but a small amount of non-English data is still present within the training corpus via CommonCrawl. The model was pretrained using a causal language modeling (CLM) objective. OPT belongs to the same family of decoder-only models like GPT-3. As such, it was…

Open weights other 2,048 tokens transformers

Model · Text generation

Ornith-1.5-9B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

Model · Text generation

Ornith-1.5-35B-A3B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

Model · Text generation

Ornith-1.0-9B-GGUF

Ornith

Aloha! Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding. This model card documents Ornith-1.0-9B, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment. Ornith-1.0-9B is a dense ~9B model (≈19 GB in bf16), so it serves comfortably on a single 80GB GPU. The recipes below stand up an OpenAI-compatible server; add --tensor-parallel-size / --tp if you want to shard across more GPUs. For a quick local test (or to script offline generation), load the model directly with Transformers. Make sure you have a recent release installed — see the Transformers installation guide; Ornith-1.0-9B requires…

Open weights mit transformers

Uncensored Qwen3.8-27B, published as GGUF quantizations with the multi token prediction (MTP) head retained and verified. Refusal behaviour has been substantially reduced, not eliminated. See Measured behaviour for the numbers. Capabilities, training data, and architecture are otherwise unchanged. - Refusal directions removed with Heretic, which co minimizes refusal count against KL divergence from the base model. No handwritten refusal removal code, no finetuning, no additional training data. - Abliteration runs at bf16 (no 4 bit quantization). the resulting LoRA is merged into the bf16 base, so the published weights are not a quantized round trip. - mtp. tensors are copied verbatim from…

Open weights apache-2.0 llama.cpp