Store › model › LLM
JiRackUltra_1b
by CMSManhattan · source Hugging Face · updated 2026-10-01
mit1.0 GB~2 GB RAMsource aliveunlabeled
JiRack Ultra 1B (CPU) A fast and efficient ~1.5B model optimized for CPU inference. The model was refactored with BitNet features and an updated tokenizer that includes new Routing, Tool call, and Ro…
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/JiRackUltra_1b and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/CMSManhattan/JiRackUltra_1b
- License: mit
- Requirements: about 2 GB of RAM, 1.0 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:
safetensorsggufqwen2text-generationternarybitnet1.58bitcpuqwen2.5deepseekefficientlow-memoryjirackweb-uiroutingtool-call
Numbers
- 2,532,192 downloads on Hugging Face
- 0 likes
- license mit
- 1.0 GB for JiRackUltra_1b_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 20:59 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 |
|---|---|---|
JiRackUltra_1b.Q6_K.gguf | Q6_K | 1.4 GB |
JiRackUltra_1b.Q8_0.gguf | Q8_0 | 1.8 GB |
JiRackUltra_1b.gguf | 3.3 GB | |
JiRackUltra_1b_Q3_K_M.gguf | Q3_K_M | 882 MB |
JiRackUltra_1b_Q4_K_M.gguf | Q4_K_M | 1.0 GB |
model.pt | 3.3 GB | |
model.safetensors | 3.3 GB |
From the source README
# JiRack Ultra 1B (CPU)
A fast and efficient ~1.5B model optimized for CPU inference. The model was refactored with BitNet features and an updated tokenizer that includes new Routing, Tool call, and Robotics tags. Built on a redesigned DeepSeek R1 architecture with native ternary (BitNet-style) support and ready-to-run GGUF quantizations.
- 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 Ternary Architedure & JiRack Tokenizer
- Benefits high quality CPU inference TQ_2 on Llama.cpp and Ollama via QAT
- Robotcs, Routing, Coding, Multimedia, Advanced tool calling via CMSManhattan/JiRackPrecisionTokenizer
PARTNERSHIP
- NVIDIA
- FISERV
# Ollama production support
- We are working to support JiRack on Ollama for production systems also
- added Jirack chat without reasoning feature https://ollama.com/cmsmanhattan
- Follow fresh Ollama platform updates
# JiRack sevice options
- Current quantizations were done from the FP16 model, but the model allows for more compression thanks to its ternary architecture.
- If you need to do ternary compression, 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 plato in training with NDA
- Convert model to TQ2_0 with support AVX2 and AVX-512 CPU instructions for high performance on CPU
- QAT for TQ_2 Llama.cpp Ternarization docs https://huggingface.co/CMSManhattan/JiRackUltra_1b/blob/main/QAT_to_Llama.cpp_GGUF_TQ2_0_JirackUltra_1b.md
- Adapts to agentic or instruct models for tool calling, using the JiRak tokenizer to enable high-quality tool calling on small models — built as a domain-specific tool expert.
- Deployment and scale
JiRack Cod…
Source: https://huggingface.co/CMSManhattan/JiRackUltra_1b
Card id model:hf:CMSManhattan/JiRackUltra_1b · collected 2026-10-02 20:59 UTC · JSON