LL

Llm Jp 3 3.7b

LlmGGUF by mmngaUpdated 2025-02-05
Download on Hugging Face
Parameters3.78B
Context4K
Layers28
Architecturellama
Smallest quant1.0 GB
Quick answer

Llm Jp 3 3.7b needs about 5.7 GB of memory at Q4_K_M (a 2.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.0 GB (IQ1_S) to 4.0 GB (Q8_0).

Llm Jp 3 3.7b – 3.78B parameter Japanese instruction model

Llm Jp 3 3.7b is a 3.78B parameter transformer model fine‑tuned for instruction following. It supports Japanese and English text. The model is released under Apache‑2.0 and can be used with llama.cpp in GGUF format.

Good at

  • Instruction following
  • Japanese language support
  • Transformer‑based architecture

Limits

  • No vision support
  • Requires 8k context for full performance
  • License is Apache‑2.0

Best for

  • Chatbot development
  • Japanese text generation
  • Instruction‑based applications

Who it’s for. Developers building Japanese language assistants or chatbots who need a large, instruction‑tuned model. The model is suitable for research and production use under an open license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.0 GB 2.9 GB
Fits Get file →
IQ1_M1.1 GB 3.0 GB
Fits Get file →
IQ2_XXS1.2 GB 3.1 GB
Fits Get file →
IQ2_XS1.2 GB 3.2 GB
Fits Get file →
IQ2_S1.3 GB 3.3 GB
Fits Get file →
IQ2_M1.4 GB 3.3 GB
Fits Get file →
Q2_K1.5 GB 3.4 GB
Fits Get file →
IQ3_XXS1.5 GB 3.4 GB
Fits Get file →
IQ3_XS1.7 GB 3.6 GB
Fits Get file →
Q3_K_S1.7 GB 3.7 GB
Fits Get file →
IQ3_S1.7 GB 3.7 GB
Fits Get file →
IQ3_M1.8 GB 3.7 GB
Fits Get file →
Q3_K_M1.9 GB 3.8 GB
Fits Get file →
Q3_K_L2.1 GB 4.0 GB
Fits Get file →
IQ4_XS2.1 GB 4.0 GB
Fits Get file →
Q4_02.2 GB 4.1 GB
Fits Get file →
IQ4_NL2.2 GB 4.1 GB
Fits Get file →
Q4_K_S2.2 GB 4.1 GB
Fits Get file →
Q4_K_M2.3 GB 4.2 GB
Fits Get file →
Q5_02.6 GB 4.6 GB
Fits Get file →
Q5_K_S2.6 GB 4.6 GB
Fits Get file →
Q5_K_M2.7 GB 4.6 GB
Fits Get file →
Q6_K3.1 GB 5.0 GB
Fits Get file →
Q8_04.0 GB 5.9 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (0.99 GB, 4.3 GB RAM). For 12 GB VRAM, IQ4_K_M (2.33 GB, 5.7 GB RAM) or Q5_K_M (2.71 GB, 6 GB RAM). For 24 GB VRAM, Q8_0 (4.02 GB, 7.3 GB RAM) gives the highest quality. Memory estimates are approximate.

What GPU do you need for Llm Jp 3 3.7b?

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: the best quant that fits is Q5_K_M (2.7 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.0 GB file, about 7.3 GB in use).

Which Llm Jp 3 3.7b quant should you choose?

Q4_K_M is the usual starting point for Llm Jp 3 3.7b: it balances file size and quality well. Here it is a 2.3 GB file.

The Q8_0 file is 4.0 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 IQ1_S at 1.0 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
Parameters3.78B
Layers28
Trained context4,096 tokens
KV cache (fp16)336 KB per token

Source

Quantized bymmnga
FamilyLlm
Licenseapache-2.0
Downloads (HF)3,027
Last updated2025-02-05

Frequently asked questions about Llm Jp 3 3.7b

How much VRAM does Llm Jp 3 3.7b need?

About 5.7 GB at Q4_K_M with an 8K context window. That is the 2.3 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 3.7b on an 8 GB GPU?

Yes, with Q8_0: the 4.0 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llm Jp 3 3.7b GGUF?

It depends on the quant: IQ1_S is 1.0 GB, IQ1_M is 1.1 GB, IQ2_XXS is 1.2 GB, IQ2_XS is 1.2 GB, IQ2_S is 1.3 GB, IQ2_M is 1.4 GB and 18 more.

What context length does Llm Jp 3 3.7b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.8 GB at 8K and 1.4 GB at 4K.

Where can I download Llm Jp 3 3.7b GGUF?

The files are on Hugging Face in the mmnga/llm-jp-3-3.7b-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 3.7b 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.

Can I run Llm Jp 3 3.7b on 8 GB VRAM?

Yes, using the IQ1_S or IQ1_M quantization which requires about 4.3–4.4 GB of RAM at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache License, Version 2.0.

Similar models

Browse all →

More from mmnga

All by mmnga →

More Llm models

All Llm →

Other small models

All small models →