SAVRN
Search Contact SAVRN

Open-weight model · Text generation

Qwen3.5-4B-Thai-CRM.GGUF

by Yothin yothinS/Qwen3.5-4B-Thai-CRM.GGUF

Qwen3.5-4B-Thai-CRM.GGUF is an open-weight model for text generation from Yothin, released under Apache License 2.0. Its published files total 27.1 GB.

This repository contains quantized versions (GGUF) of the yothinS/Qwen3.5-4B-CRM model, which is a fine-tuned version of the Qwen series optimized for Customer Relationship Management (CRM) tasks, customer support, and business communications.

Parameters—
Context—
Weights27.1 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By Yothin, published under apache-2.0, revision 276207b9e772.

This repository contains quantized versions (GGUF) of the yothinS/Qwen3.5-4B-CRM model, which is a fine-tuned version of the Qwen series optimized for Customer Relationship Management (CRM) tasks, customer support, and business communications. These quantized versions drastically reduce memory usage and accelerate inference speeds, allowing you to run a powerful 4-billion parameter CRM assistant on consumer hardware, laptops, and edge devices. This repository provides GGUF format files optimized for inference using llama.cpp, Ollama, LM Studio, and other compatible software. Note: Memory Required includes the model weight footprint plus a standard context window buffer. To run the GGUF…

Read Yothin's full model card

Qwen3.5-4B-CRM - Quantized Versions

This repository contains quantized versions (GGUF) of the yothinS/Qwen3.5-4B-CRM model, which is a fine-tuned version of the Qwen series optimized for Customer Relationship Management (CRM) tasks, customer support, and business communications.

These quantized versions drastically reduce memory usage and accelerate inference speeds, allowing you to run a powerful 4-billion parameter CRM assistant on consumer hardware, laptops, and edge devices.


Available Formats & Model Files

This repository provides GGUF format files optimized for inference using llama.cpp, Ollama, LM Studio, and other compatible software.

Format Recommended File / Quantization File Size Memory Required Target Hardware / Use Case
GGUF Qwen3.5-4B-CRM-f16.gguf 8.67 GB ~9.5+ GB High-end PC / Apple Silicon Mac. Maximum precision, no quantization loss.
GGUF Qwen3.5-4B-Thai-CRM-Q8_0.gguf 4.61 GB ~5.2 GB Near-lossless quality. Balanced CPU/GPU inference with high precision.
GGUF Qwen3.5-4B-Thai-CRM-Q6_K.gguf 3.56 GB ~4.2 GB Good balance of generation quality and performance for mid-range hardware.
GGUF Qwen3.5-4B-Thai-CRM-Q5_K_M.gguf 3.16 GB ~3.8 GB Recommended for general use. Best trade-off between file size and capabilities.
GGUF Qwen3.5-4B-Thai-CRM-Q4_K_M.gguf 2.78 GB ~3.4 GB Standard 4-bit quantization. Ideal for low-VRAM devices or quick testing.
GGUF Qwen3.5-4B-Thai-CRM-Q3_K_M.gguf 2.32 GB ~2.9 GB Low memory footprint. Noticeable drop in response accuracy.
GGUF Qwen3.5-4B-Thai-CRM-Q2_K.gguf 1.96 GB ~2.5 GB Minimum size. Designed for highly constrained environments or mobile devices.

Note: Memory Required includes the model weight footprint plus a standard context window buffer.

Quick Start & Usage Guide

1. Using GGUF Format with llama.cpp

To run the GGUF version locally in your terminal, use the following commands:


# Run inference with the downloaded .gguf file
./llama-cli -m ./Qwen3.5-4B-CRM-Q4_K_M.gguf -n 512 --color -p "<|im_start|>system\nYou are a helpful CRM assistant.<|im_end|>\n<|im_start|>user\nHelp me write a follow-up email to a client who hasn't responded in 3 days.<|im_end|>\n<|im_start|>assistant\n"

Model Capabilities & Intended Use

This quantized model retains the core capabilities of the base yothinS/Qwen3.5-4B-CRM model, including: * CRM Automation: Generating follow-up emails, sales pitches, and support ticket summaries. * Multilingual Business Context: Strong comprehension and generation of professional responses in English and Thai. * Customer Support: Resolving queries with appropriate professional empathy, clarity, and tone alignment.


Quantization Method & Evaluation Notes

  • GGUF weights were processed using the standard llama.cpp quantization toolkits.
  • Expect minimal perplexity degradation on 8-bit versions and minor trade-offs in edge-case reasoning on 4-bit configurations, which is normal across compact architectures.

Licensing

This model is distributed under the Apache 2.0 License, inherited from the base Qwen framework. Please adhere to the usage constraints and terms defined by Alibaba Qwen team.

Identity and Version

Repository
yothinS/Qwen3.5-4B-Thai-CRM.GGUF
Publisher
Yothin
Task
Text generation
Modality
Text
Library
Not stated by the source
Parameters
Not stated by the source
Languages
crm, awq
Revision
276207b9e772b814bd566469cf5feaa7329b4aec
First published
2026-10-05
Last updated
2026-10-07

Files and Weights

9 files, 27.1 GB in total. The weights are 7 files totalling 27.1 GB in gguf.

Weights7 files · 27.1 GB
Documentation1 file · 3.5 KB
Repository1 file · 2.5 KB
Every file
FileTypeSizeSHA-256
Qwen3.5-4B-CRM-f16.ggufWeights8.7 GB d691676ee400
Qwen3.5-4B-Thai-CRM-Q2_K.ggufWeights2.0 GB c75ad72ad0d1
Qwen3.5-4B-Thai-CRM-Q3_K_M.ggufWeights2.3 GB e72ce0ee1ec9
Qwen3.5-4B-Thai-CRM-Q4_K_M.ggufWeights2.8 GB 1743946fed54
Qwen3.5-4B-Thai-CRM-Q5_K_M.ggufWeights3.2 GB d20fe8027579
Qwen3.5-4B-Thai-CRM-Q6_K.ggufWeights3.6 GB e618183396ac
Qwen3.5-4B-Thai-CRM-Q8_0.ggufWeights4.6 GB 3f5b37d55398
README.mdDocumentation3.5 KB —
.gitattributesRepository2.5 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
27.1 GB
Download from Yothin

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

Built From

  • Derived from yothinS/Qwen3.5-4B-CRM
  • Quantized from yothinS/Qwen3.5-4B-CRM

Memory Requirements

PrecisionWeights in memory
As published27.1 GB

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

Questions About Qwen3.5-4B-Thai-CRM.GGUF

Can I use Qwen3.5-4B-Thai-CRM.GGUF commercially?

Yes. Qwen3.5-4B-Thai-CRM.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.

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

Ternary-Bonsai-2-27B-gguf

Prism ML

Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) - \~5.9 GB language model (down from \~54 GB FP16) — full 27B-class reasoning on a standard laptop or a single GPU - 98.2% of FP16 intelligence retained: 84.78 average across 14 thinking-mode benchmarks — far above the conventional IQ2XXS build (72.59) at about 82% of its footprint, and within 0.4 points of UD-Q4KXL at three times the footprint - Retains thinking, reasoning, and agentic behavior deep in the sub-4-bit regime, where conventional low-bit representations collapse: math within half a point of full precision (96.57), coding level with the baseline (89.42), agentic tool calling at 74.92…

Open weights apache-2.0 llama.cpp

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