JiRackDeltaNet 27b needs about 19.5 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 10.9 GB (Q2_K) to 54.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
JiRackDeltaNet 27b – a 27B Qwen3.8‑style DeltaNet model optimized for CPU inference
JiRackDeltaNet 27b is a 27 billion‑parameter model built on a Qwen3.8‑style DeltaNet architecture with hybrid attention and SSM. It supports advanced tool calling, routing, media, vision, sound, and robotics tags via its custom tokenizer. The model is released under the MIT license and is available as GGUF quantizations for llama.cpp and Ollama.
Good at
- Advanced tool calling and routing
- Robotics and multimedia reasoning
- High‑quality CPU inference with QAT
Limits
- No vision support in the base model
- Large context length requires high VRAM for large quantizations
- Requires a 27 billion‑parameter model for full capability
Best for
- Deploying as a fast CPU inference agent
- Integrating into RAG pipelines with tool calling
- Running on cloud‑ready infrastructure for cost savings
Who it’s for. Developers and researchers needing a large, efficient model for tool‑based tasks and robotics. The model is suitable for users who prefer CPU inference and want a ready‑to‑run GGUF quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 10.9 GB | 13.5 GB | Too big | Get file → | |
| Q3_K_M | 13.5 GB | 16.2 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 19.5 GB | Too big | Get file → | |
| Q6_K | 22.4 GB | 25.1 GB | Too big | Get file → | |
| Q8_0 | 29.0 GB | 31.7 GB | Too big | Get file → | |
| — | 54.7 GB | 57.3 GB | Too big | Get file → |
For 8 GB VRAM, use the Q2_K quant (10.86 GB file, ~13.5 GB memory). For 12 GB VRAM, Q3_K_M (13.5 GB file, ~16.2 GB memory) is a good balance. If you have 16 GB VRAM, Q4_K_M (16.81 GB file, ~19.5 GB memory) provides higher quality.
What GPU do you need for JiRackDeltaNet 27b?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q2_K (10.9 GB file, about 13.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (16.8 GB file, about 19.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (29.0 GB file, about 31.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (29.0 GB file, about 31.7 GB in use).
Which JiRackDeltaNet 27b quant should you choose?
Q4_K_M is the usual starting point for JiRackDeltaNet 27b: it balances file size and quality well. Here it is a 16.8 GB file.
The Q8_0 file is 29.0 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 10.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about JiRackDeltaNet 27b
How much VRAM does JiRackDeltaNet 27b need?
About 19.5 GB at Q4_K_M with an 8K context window. That is the 16.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run JiRackDeltaNet 27b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of JiRackDeltaNet 27b GGUF?
It depends on the quant: Q2_K is 10.9 GB, Q3_K_M is 13.5 GB, Q4_K_M is 16.8 GB, Q6_K is 22.4 GB, Q8_0 is 29.0 GB, file is 54.7 GB.
What context length does JiRackDeltaNet 27b support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download JiRackDeltaNet 27b GGUF?
The files are on Hugging Face in the CMSManhattan/JiRackDeltaNet_27b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does JiRackDeltaNet 27b use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run JiRackDeltaNet 27b on 8 GB VRAM?
Yes, using the Q2_K quantization which requires about 13.5 GB of VRAM at 8k context.
Does the model support vision tasks?
The base model does not include vision support; it focuses on tool calling, routing, and robotics.