LL

Llm Jp 3 8x13b Instruct3

LlmGGUF by mmngaUpdated 2025-03-28
Download on Hugging Face
Parameters73.2B
Context4K
Layers40
Architecturellama
Smallest quant16.3 GB
Quick answer

Llm Jp 3 8x13b Instruct3 needs about 52.6 GB of memory at Q4_K_M (a 45.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 19 quants, from 16.3 GB (IQ1_S) to 45.4 GB (Q4_K_M).

Llm Jp 3 8x13b Instruct3 is a 73.2B-parameter Llm model in GGUF format, quantized by mmnga. Its trained context length is 4K tokens. The repository has 19 quant files, from 16.3 GB (IQ1_S) to 45.4 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S16.3 GB 20.1 GB
Too big Get file →
IQ1_M17.8 GB 21.7 GB
Too big Get file →
IQ2_XXS20.4 GB 24.3 GB
Too big Get file →
IQ2_XS22.5 GB 26.3 GB
Too big Get file →
IQ2_S22.8 GB 26.7 GB
Too big Get file →
IQ2_M24.9 GB 28.7 GB
Too big Get file →
Q2_K28.5 GB 32.3 GB
Too big Get file →
IQ3_XXS29.9 GB 33.7 GB
Too big Get file →
IQ3_XS31.6 GB 35.5 GB
Too big Get file →
Q3_K_S33.2 GB 37.1 GB
Too big Get file →
IQ3_S33.2 GB 37.1 GB
Too big Get file →
IQ3_M34.7 GB 38.6 GB
Too big Get file →
Q3_K_M36.4 GB 40.2 GB
Too big Get file →
Q3_K_L38.8 GB 42.7 GB
Too big Get file →
IQ4_XS40.3 GB 44.2 GB
Too big Get file →
Q4_042.3 GB 46.2 GB
Too big Get file →
IQ4_NL42.5 GB 46.3 GB
Too big Get file →
Q4_K_S42.8 GB 46.7 GB
Too big Get file →
Q4_K_M45.4 GB 49.3 GB
Too big Get file →

What GPU do you need for Llm Jp 3 8x13b Instruct3?

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: the best quant that fits is IQ1_S (16.3 GB file, about 23.5 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ2_S (22.8 GB file, about 30.0 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ4_XS (40.3 GB file, about 47.5 GB in use).

Which Llm Jp 3 8x13b Instruct3 quant should you choose?

Q4_K_M is the usual starting point for Llm Jp 3 8x13b Instruct3: it balances file size and quality well. Here it is a 45.4 GB file.

If memory is tight, the smallest file is IQ1_S at 16.3 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
Parameters73.2B (approximate, mixture of experts)
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymmnga
FamilyLlm
Licenseapache-2.0
Downloads (HF)277
Last updated2025-03-28

Frequently asked questions about Llm Jp 3 8x13b Instruct3

How much VRAM does Llm Jp 3 8x13b Instruct3 need?

About 52.6 GB at Q4_K_M with an 8K context window. That is the 45.4 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 3 8x13b Instruct3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 23.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llm Jp 3 8x13b Instruct3 GGUF?

It depends on the quant: IQ1_S is 16.3 GB, IQ1_M is 17.8 GB, IQ2_XXS is 20.4 GB, IQ2_XS is 22.5 GB, IQ2_S is 22.8 GB, IQ2_M is 24.9 GB and 13 more.

What context length does Llm Jp 3 8x13b Instruct3 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download Llm Jp 3 8x13b Instruct3 GGUF?

The files are on Hugging Face in the mmnga/llm-jp-3-8x13b-instruct3-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 3 8x13b Instruct3 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 large models

All large models →