QW

JiRackDeltaNet 180b

QwenGGUF by CMSManhattanUpdated 2026-10-28
Download on Hugging Face
Parameters177B
Context256K
Layers48
Architectureqwen4exp
Smallest quant94.1 GB
Quick answer

JiRackDeltaNet 180b needs about 120.5 GB of memory at Q4_K_M (a 119.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 94.1 GB (Q3_K_M) to 354.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

JiRackDeltaNet 180B – a 180B Mixture‑of‑Experts LLM for CPU inference

JiRackDeltaNet 180B is a 180‑billion‑parameter MoE model based on Qwen3.8‑Flash‑Next. It uses Gated DeltaNet and Qwen Sparse Attention, with only ~6 B active parameters per token. The model is text‑only and supports tool calling.

Good at

  • Efficient CPU inference with MoE
  • Large context handling
  • Tool‑call workflows

Limits

  • Text‑only, no vision
  • Requires large VRAM for full model
  • License is other, not open source

Best for

  • RAG deployments
  • Advanced tool‑calling tasks
  • CPU‑centric inference

Who it’s for. Engineers and researchers needing high‑quality inference on commodity CPUs. The model is suitable for cloud‑ready deployments where cost per token is critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M94.1 GB 95.4 GB
Too big Get file →
Q4_K_M119.2 GB 120.5 GB
Too big Get file →
—354.0 GB (7 parts) 355.3 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_M (94 GB file, ~95 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (119 GB file, ~120 GB memory). The full unquantized shard set requires ~355 GB memory and is not practical for typical GPUs.

What GPU do you need for JiRackDeltaNet 180b?

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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which JiRackDeltaNet 180b quant should you choose?

Q4_K_M is the usual starting point for JiRackDeltaNet 180b: it balances file size and quality well. Here it is a 119.2 GB file.

If memory is tight, the smallest file is Q3_K_M at 94.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen4exp
Parameters177B (approximate, mixture of experts)
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized byCMSManhattan
FamilyQwen
Licenseother
Downloads (HF)6,694
Last updated2026-10-28

Frequently asked questions about JiRackDeltaNet 180b

How much VRAM does JiRackDeltaNet 180b need?

About 120.5 GB at Q4_K_M with an 8K context window. That is the 119.2 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 180b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 95.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of JiRackDeltaNet 180b GGUF?

It depends on the quant: Q3_K_M is 94.1 GB, Q4_K_M is 119.2 GB, file is 354.0 GB.

What context length does JiRackDeltaNet 180b support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download JiRackDeltaNet 180b GGUF?

The files are on Hugging Face in the CMSManhattan/JiRackDeltaNet_180b 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 180b use?

Hugging Face lists the license as other. 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 180B on 8 GB VRAM?

No. The smallest quantized version needs about 95 GB of VRAM at 8k context. Even 16 GB VRAM is insufficient for the full model.

Does the model support image input?

No. The JiRack build is currently text‑only; image and video support is only in the base Qwen3.8‑Flash‑Next.

What is the context length of this model?

The model was trained with a context of 262,144 tokens, but practical inference is limited by VRAM and quantization.

Other GGUFs of Qwen3.8-Flash-Next

Similar models

Browse all →

More from CMSManhattan

All by CMSManhattan →

More Qwen models

All Qwen →

Other large models

All large models →