🧠

Model

Qwen 3.5 28b A3b Reap I1 Gguf

Name: Qwen 3.5 28b A3b Reap I1 Gguf
Author: mradermacher

by mradermacher hf-model--mradermacher--qwen-3.5-28b-a3b-reap-i1-gguf

Nexus Index

40.5 Top 100%

S: Semantic 50

A: Authority 0

P: Popularity 39

R: Recency 98

Q: Quality 30

Tech Context

28 Params

4.096K Ctx

Vital Performance

5.2K DL / 30D

0.0%

Source →

Audited 40.5 FNI Score

28B Params

4k Context

5.2K Downloads

24G GPU ~23GB Est. VRAM

Commercial APACHE License

Model Information Summary
Entity Passport
Registry ID	hf-model--mradermacher--qwen-3.5-28b-a3b-reap-i1-gguf
License	Apache-2.0
Provider	huggingface

💾

Compute Threshold

~22.3GB VRAM

Interactive

Analyze Hardware

Hardware Compatibility Test

▼

* Static estimation for 4-Bit Quantization.

📜

Cite this model

Academic & Research Attribution

BibTeX

@misc{hf_model__mradermacher__qwen_3.5_28b_a3b_reap_i1_gguf,
  author = {mradermacher},
  title = {Qwen 3.5 28b A3b Reap I1 Gguf Model},
  year = {2026},
  howpublished = {\url{https://huggingface.co/mradermacher/qwen-3.5-28b-a3b-reap-i1-gguf}},
  note = {Accessed via Free2AITools Knowledge Fortress}
}

APA Style

mradermacher. (2026). Qwen 3.5 28b A3b Reap I1 Gguf [Model]. Free2AITools. https://huggingface.co/mradermacher/qwen-3.5-28b-a3b-reap-i1-gguf

🔬Technical Deep Dive

Full Specifications [+]

Quick Commands

🦙 Ollama Run

ollama run qwen-3.5-28b-a3b-reap-i1-gguf

🤗 HF Download

huggingface-cli download mradermacher/qwen-3.5-28b-a3b-reap-i1-gguf

📦 Install Lib

pip install -U transformers

⚖️ Nexus Index V2.0

Methodology Index Protocol

40.5

TOP 100% SYSTEM IMPACT

Semantic (S) 50

Authority (A) 0

Popularity (P) 39

Recency (R) 98

Quality (Q) 30

💬 Index Insight

FNI V2.0 for Qwen 3.5 28b A3b Reap I1 Gguf: Semantic (S:50), Authority (A:0), Popularity (P:39), Recency (R:98), Quality (Q:30).

Free2AITools Nexus Index

Verification Authority

HuggingFace API GitHub Metadata Arxiv Citation DB System Audit

Unbiased Data Node Refresh: VFS Live

---

🚀 What's Next?

📊

Find Training Datasets

Discover datasets compatible with this model

📈

Compare Benchmarks

See how this model ranks on standard tests

⚡

Technical Deep Dive

About

weighted/imatrix quants of https://huggingface.co/0xSero/Qwen-3.5-28B-A3B-REAP

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/Qwen-3.5-28B-A3B-REAP-GGUF

This is a vision model - mmproj files (if any) will be in the static repository.

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link	Type	Size/GB	Notes
GGUF	imatrix	0.3	imatrix file (for creating your own quants)
GGUF	i1-IQ1_S	6.3	for the desperate
GGUF	i1-IQ1_M	6.9	mostly desperate
GGUF	i1-IQ2_XXS	7.9
GGUF	i1-IQ2_XS	8.7
GGUF	i1-IQ2_S	8.9
GGUF	i1-IQ2_M	9.7
GGUF	i1-Q2_K_S	10.1	very low quality
GGUF	i1-Q2_K	10.7	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	11.3	lower quality
GGUF	i1-IQ3_XS	12.0
GGUF	i1-Q3_K_S	12.5	IQ3_XS probably better
GGUF	i1-IQ3_S	12.6	beats Q3_K*
GGUF	i1-IQ3_M	12.7
GGUF	i1-Q3_K_M	13.8	IQ3_S probably better
GGUF	i1-Q3_K_L	14.9	IQ3_M probably better
GGUF	i1-IQ4_XS	15.4
GGUF	i1-Q4_0	16.3	fast, low quality
GGUF	i1-Q4_K_S	16.3	optimal size/speed/quality
GGUF	i1-Q4_K_M	17.4	fast, recommended
GGUF	i1-Q4_1	17.9
GGUF	i1-Q5_K_S	19.7
GGUF	i1-Q5_K_M	20.3
GGUF	i1-Q6_K	23.3	practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

⚠️ Incomplete Data

Some information about this model is not available. Use with Caution - Verify details from the original source before relying on this data.

View Original Source →

📝 Limitations & Considerations

• Benchmark scores may vary based on evaluation methodology and hardware configuration.
• VRAM requirements are estimates; actual usage depends on quantization and batch size.
• FNI scores are relative rankings and may change as new models are added.
⚠ License Unknown: Verify licensing terms before commercial use.

Social Proof

HuggingFace Hub

5.2KDownloads

Hub Discussions

🤗 Data Source: Hugging Face ↗

🔄 Daily sync (03:00 UTC)

AI Summary: Based on Hugging Face metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseℹ️ Verify with original source

🛡️ Model Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id: hf-model--mradermacher--qwen-3.5-28b-a3b-reap-i1-gguf
slug: mradermacher--qwen-3.5-28b-a3b-reap-i1-gguf
source: huggingface
author: mradermacher
license: Apache-2.0
tags: transformers, gguf, moe, pruning, reap, qwen3, expert-pruning, en, base_model:0xsero/qwen-3.5-28b-a3b-reap, base_model:quantized:0xsero/qwen-3.5-28b-a3b-reap, license:apache-2.0, endpoints_compatible, region:us, imatrix, conversational

⚙️ Technical Specs

architecture: null
params billions: 28
context length: 4,096
pipeline tag
vram gb: 22.3
vram is estimated: true
vram formula: VRAM ≈ (params * 0.75) + 0.8GB (KV) + 0.5GB (OS)

📊 Engagement & Metrics

downloads: 5,199
stars: 0
forks: 0

Data indexed from public sources. Updated daily.

Welcome to Free2AI Tools!

Smart Search

FNI Score

You're All Set!