JI

JiRackUltra_14b

JirackultraGGUF by CMSManhattanUpdated 2026-10-29
Download on Hugging Face
Parameters14.8B
Context128K
Layers48
Architectureqwen2
Smallest quant5.8 GB
Quick answer

JiRackUltra_14b needs about 11.1 GB of memory at Q4_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 7 quants, from 5.8 GB (Q2_K) to 29.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

JiRackUltra_14b – a 14B CPU‑optimized Qwen2 model with ternary support

JiRackUltra_14b is a 15‑billion‑parameter Qwen2 model optimized for CPU inference. It uses a ternary BitNet architecture and a tokenizer with Routing, Media, Vision, Sound, Tool call, and Robotics tags. The model is released under the MIT license and supports tool‑calling abilities.

Good at

  • Fast CPU inference with QAT
  • Tool‑calling via specialized tokenizer
  • RAG deployments on cloud

Limits

  • No vision support in current quantizations
  • Requires 8‑k context for memory estimates
  • Large model size for higher quants

Best for

  • CPU‑based RAG systems
  • Tool‑calling agents
  • Cloud‑ready inference

Who it’s for. Developers building CPU‑centric LLM services who need efficient inference and tool‑calling. The model is suitable for on‑prem or cloud deployments where GPU resources are limited.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.8 GB 7.9 GB
Tight Get file →
Q3_K_M7.3 GB 9.4 GB
Too big Get file →
Q4_K_M9.0 GB 11.1 GB
Too big Get file →
Q5_K_M10.5 GB 12.6 GB
Too big Get file →
Q6_K12.1 GB 14.2 GB
Too big Get file →
Q8_015.7 GB 17.8 GB
Too big Get file →
—29.5 GB 31.7 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (5.77 GB, ~7.9 GB RAM). For 12 GB VRAM, Q3_K_M (7.34 GB, ~9.4 GB RAM) or Q4_K_M (8.99 GB, ~11.1 GB RAM). For 16 GB VRAM, Q5_K_M (10.51 GB, ~12.6 GB RAM) or Q6_K (12.12 GB, ~14.2 GB RAM).

What GPU do you need for JiRackUltra_14b?

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: the best quant that fits is Q2_K (5.8 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (9.0 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (12.1 GB file, about 14.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.7 GB file, about 17.8 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (29.5 GB file, about 31.7 GB in use).

Which JiRackUltra_14b quant should you choose?

Q4_K_M is the usual starting point for JiRackUltra_14b: it balances file size and quality well. Here it is a 9.0 GB file.

The Q8_0 file is 15.7 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 5.8 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

Architectureqwen2
Parameters14.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)192 KB per token

Source

Quantized byCMSManhattan
Licensemit
Downloads (HF)10,296
Last updated2026-10-29

Frequently asked questions about JiRackUltra_14b

How much VRAM does JiRackUltra_14b need?

About 11.1 GB at Q4_K_M with an 8K context window. That is the 9.0 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 JiRackUltra_14b on an 8 GB GPU?

Yes, with Q2_K: the 5.8 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of JiRackUltra_14b GGUF?

It depends on the quant: Q2_K is 5.8 GB, Q3_K_M is 7.3 GB, Q4_K_M is 9.0 GB, Q5_K_M is 10.5 GB, Q6_K is 12.1 GB, Q8_0 is 15.7 GB and 1 more.

What context length does JiRackUltra_14b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download JiRackUltra_14b GGUF?

The files are on Hugging Face in the CMSManhattan/JiRackUltra_14b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does JiRackUltra_14b 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 JiRackUltra_14b on 8 GB VRAM?

Yes, the Q2_K quantization is 5.77 GB and requires about 7.9 GB RAM at 8‑k context, fitting within 8 GB VRAM.

Does the model support vision tasks?

No, the current quantizations do not include vision support.

What license applies to this model?

The model is released under the MIT license.

Similar models

Browse all →

More from CMSManhattan

All by CMSManhattan →

More Jirackultra models

All Jirackultra →

Other medium models

All medium models →