LL

llm jp 1.8bx24 combined

LlmGGUF by mmngaUpdated 2025-04-02
Download on Hugging Face
Parameters26.2B
Context4K
Layers24
Architecturellama
Smallest quant5.4 GB
Quick answer

llm jp 1.8bx24 combined needs about 18.0 GB of memory at Q4_K_M (a 15.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 5.4 GB (IQ1_S) to 27.8 GB (Q8_0).

llm jp 1.8bx24 combined is a 26.2B-parameter Llm model in GGUF format, quantized by mmnga. Its trained context length is 4K tokens. The repository has 24 quant files, from 5.4 GB (IQ1_S) to 27.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S5.4 GB 6.7 GB
Fits Get file →
IQ1_M6.0 GB 7.3 GB
Tight Get file →
IQ2_XXS7.0 GB 8.3 GB
Too big Get file →
IQ2_XS7.7 GB 9.0 GB
Too big Get file →
IQ2_S7.9 GB 9.2 GB
Too big Get file →
IQ2_M8.6 GB 9.9 GB
Too big Get file →
Q2_K9.6 GB 10.9 GB
Too big Get file →
IQ3_XXS10.1 GB 11.4 GB
Too big Get file →
IQ3_XS10.7 GB 12.0 GB
Too big Get file →
Q3_K_S11.3 GB 12.6 GB
Too big Get file →
IQ3_S11.3 GB 12.6 GB
Too big Get file →
IQ3_M11.5 GB 12.8 GB
Too big Get file →
Q3_K_M12.5 GB 13.8 GB
Too big Get file →
Q3_K_L13.6 GB 14.9 GB
Too big Get file →
IQ4_XS14.0 GB 15.3 GB
Too big Get file →
Q4_014.8 GB 16.1 GB
Too big Get file →
IQ4_NL14.8 GB 16.1 GB
Too big Get file →
Q4_K_S14.9 GB 16.2 GB
Too big Get file →
Q4_K_M15.9 GB 17.2 GB
Too big Get file →
Q5_018.0 GB 19.3 GB
Too big Get file →
Q5_K_S18.0 GB 19.3 GB
Too big Get file →
Q5_K_M18.6 GB 19.9 GB
Too big Get file →
Q6_K21.5 GB 22.8 GB
Too big Get file →
Q8_027.8 GB 29.1 GB
Too big Get file →

What GPU do you need for llm jp 1.8bx24 combined?

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 IQ1_S (5.4 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q2_K (9.6 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_L (13.6 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (21.5 GB file, about 23.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (27.8 GB file, about 29.9 GB in use).

Which llm jp 1.8bx24 combined quant should you choose?

Q4_K_M is the usual starting point for llm jp 1.8bx24 combined: it balances file size and quality well. Here it is a 15.9 GB file.

The Q8_0 file is 27.8 GB, about 1.8 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 IQ1_S at 5.4 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

Architecturellama
Parameters26.2B (approximate, mixture of experts)
Layers24
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymmnga
FamilyLlm
Licenseapache-2.0
Downloads (HF)202
Last updated2025-04-02

Frequently asked questions about llm jp 1.8bx24 combined

How much VRAM does llm jp 1.8bx24 combined need?

About 18.0 GB at Q4_K_M with an 8K context window. That is the 15.9 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 llm jp 1.8bx24 combined on an 8 GB GPU?

Yes, with IQ1_S: the 5.4 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of llm jp 1.8bx24 combined GGUF?

It depends on the quant: IQ1_S is 5.4 GB, IQ1_M is 6.0 GB, IQ2_XXS is 7.0 GB, IQ2_XS is 7.7 GB, IQ2_S is 7.9 GB, IQ2_M is 8.6 GB and 18 more.

What context length does llm jp 1.8bx24 combined support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download llm jp 1.8bx24 combined GGUF?

The files are on Hugging Face in the mmnga/llm-jp-1.8bx24-combined-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does llm jp 1.8bx24 combined use?

Hugging Face lists the license as apache-2.0. 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 mmnga

All by mmnga →

More Llm models

All Llm →

Other medium models

All medium models →