JA

Jah 1.0

JahGGUF by RMDWLLCUpdated 2026-06-30
Download on Hugging Face
Parameters381B
Context1024K
Layers78
Architectureglm-dsa
Smallest quant181.8 GB
Quick answer

Jah 1.0 needs about 183.7 GB of memory at Q3_K_M (a 181.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Jah 1.0 is a 381B-parameter Jah model in GGUF format, quantized by RMDWLLC. Its trained context length is 1024K tokens. The repository has 1 quant file, from 181.8 GB (Q3_K_M) to 181.8 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M181.8 GB (5 parts) 183.7 GB
Too big Get file →

What GPU do you need for Jah 1.0?

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 Jah 1.0 quant should you choose?

Q3_K_M (181.8 GB) is the middle option in this repository. 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

Architectureglm-dsa
Parameters381B (approximate, mixture of experts)
Layers78
Trained context1,048,576 tokens
KV cache (fp16)166 KB per token

Source

Quantized byRMDWLLC
FamilyJah
RepositoryRMDWLLC/Jah-1.0
Licensemit
Downloads (HF)12
Last updated2026-06-30

Frequently asked questions about Jah 1.0

How much VRAM does Jah 1.0 need?

About 183.7 GB at Q3_K_M with an 8K context window. That is the 181.8 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 Jah 1.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 183.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Jah 1.0 GGUF?

It depends on the quant: Q3_K_M is 181.8 GB.

What context length does Jah 1.0 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download Jah 1.0 GGUF?

The files are on Hugging Face in the RMDWLLC/Jah-1.0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Jah 1.0 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.

Similar models

Browse all →

More from RMDWLLC

All by RMDWLLC →

Other large models

All large models →