Store › model › LLM
JiRackDeltaNet_27b
by CMSManhattan · source Hugging Face · updated 2026-10-01
mit16 GB~19 GB RAMsource aliveunlabeled
Qwen 3.8 27b migrated to Ternary Architedure - Benefits high quality CPU inference TQ2 on Llama.cpp and Ollama via QAT - Robotcs, Routing, Coding, Multimedia, Advanced tool calling via JiRackDeltaNet…
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:CMSManhattan/JiRackDeltaNet_27b and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/CMSManhattan/JiRackDeltaNet_27b
- License: mit
- Requirements: about 19 GB of RAM, 16 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp, ollama.
- Tags:
safetensorsggufqwen3_5_texttext-generationdeltanetqwen3.8cpuefficientlow-memoryternarybitnetjirackweb-uiroutingtool-callrobotics
Numbers
- 553,715 downloads on Hugging Face
- 3 likes
- license mit
- 16 GB for JiRackDeltaNet_27b.Q4_K_M.gguf
- 327,838 npm downloads a week for node-llama-cpp
- latest node-llama-cpp@3.22.1
Numbers as of 2026-10-02 21:00 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
JiRackDeltaNet_27b.Q2_K.gguf | Q2_K | 10 GB |
JiRackDeltaNet_27b.Q3_K_M.gguf | Q3_K_M | 13 GB |
JiRackDeltaNet_27b.Q4_K_M.gguf | Q4_K_M | 16 GB |
JiRackDeltaNet_27b.Q6_K.gguf | Q6_K | 21 GB |
JiRackDeltaNet_27b.Q8_0.gguf | Q8_0 | 27 GB |
JiRackDeltaNet_27b.gguf | 51 GB | |
model.pt | 50 GB | |
model.safetensors | 51 GB |
From the source README
# Qwen 3.8 27b migrated to Ternary Architedure
- Benefits high quality CPU inference TQ_2 on Llama.cpp and Ollama via QAT
- Robotcs, Routing, Coding, Multimedia, Advanced tool calling via JiRackDeltaNetTokenizer
- JiRack DeltaNet understand video and images that best for Robotics also
## PARTNERSHIP
- NVIDIA
- FISERV
# JiRack DeltaNet 27B (CPU)
A fast and efficient 27B model optimized for CPU inference. Built on a Qwen3.8-style DeltaNet architecture (hybrid attention + SSM), with an updated tokenizer that includes Routing, Media, Vision, Sound, Tool call, and Robotics tags. Ready-to-run GGUF quantizations, and native Ollama support with reasoning disabled by default for fast, direct responses.
- JiRack is a cloud-ready model that helps save money on cloud infrastructure. It can be used as an expert model in RAG deployments, with the ONNX JiRack Java server as an alternative.
# JiRack service options
- Current quantizations were done from the FP16 model.
- If you need custom compression or fine-tuning, please write to me and I'll perform QAT from your dataset, tailored specifically to your task.
- Plus double QAT via ONNX QAT.
- Adapt train process to avoid catastrophic forgetting with NDA
- Adapt train process to avoid fast plateau in training with NDA
- Adapts to agentic or instruct models for tool calling, using the JiRack tokenizer to enable high-quality tool calling on small models — built as a domain-specific tool expert.
- Deployment and scale
# JiRack Codding Agent IDE
- It is Agent Coding IDE for JiRack Models to run via Ollama on home PC
- It good choose for Agent Coding IDE such as Cursor , Windsurf IDE or Devin IDE etc but more safe that ask you to apply changes and review.
- Web site with fresh Web Dev UI https://www.jirack.com
- Plugin https://marketplace.eclipse.org/content/jirack-coding-agent
- Final release version https://huggingface.co/CMSManhattan/JiRackD…
Source: https://huggingface.co/CMSManhattan/JiRackDeltaNet_27b
Card id model:hf:CMSManhattan/JiRackDeltaNet_27b · collected 2026-10-02 21:00 UTC · JSON