PH

Borea Phi 3.5 Mini Instruct Jp

PhiGGUF by mmngaUpdated 2024-08-21
Download on Hugging Face
Parameters3.82B
Context128K
Layers32
Architecturephi3
Smallest quant0.8 GB
Quick answer

Borea Phi 3.5 Mini Instruct Jp needs about 6.1 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 0.8 GB (IQ1_S) to 4.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Borea Phi 3.5 Mini Instruct Jp – 3.82B Phi3 model in GGUF format

Borea Phi 3.5 Mini Instruct Jp is a 3.82B parameter Phi3 model converted to GGUF by mmnga. It supports a 131072 token context window and is released under the MIT license. The model is available in multiple quantizations ranging from IQ1_S to Q8_0.

Good at

  • Large context handling
  • Japanese instruction following
  • Low‑memory inference

Limits

  • No vision support
  • Requires 4.6–7.8 GB VRAM for 8 k context
  • License is MIT – no restrictions on commercial use

Best for

  • Chatbots needing long context
  • Japanese text generation
  • Fine‑tuning on small datasets

Who it’s for. Developers and researchers who need a Japanese‑focused Phi3 model with a large context window and flexible quantization options. The model is suitable for local deployment on consumer GPUs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.8 GB 4.6 GB
Fits Get file →
IQ1_M0.9 GB 4.6 GB
Fits Get file →
IQ2_XXS1.0 GB 4.8 GB
Fits Get file →
IQ2_XS1.2 GB 4.9 GB
Fits Get file →
IQ2_S1.2 GB 4.9 GB
Fits Get file →
IQ2_M1.3 GB 5.0 GB
Fits Get file →
Q2_K1.4 GB 5.1 GB
Fits Get file →
IQ3_XXS1.5 GB 5.2 GB
Fits Get file →
IQ3_XS1.6 GB 5.3 GB
Fits Get file →
Q3_K_S1.7 GB 5.4 GB
Fits Get file →
IQ3_S1.7 GB 5.4 GB
Fits Get file →
IQ3_M1.9 GB 5.6 GB
Fits Get file →
Q3_K_M2.0 GB 5.7 GB
Fits Get file →
IQ4_XS2.1 GB 5.8 GB
Fits Get file →
Q3_K_L2.1 GB 5.8 GB
Fits Get file →
Q4_02.2 GB 5.9 GB
Fits Get file →
IQ4_NL2.2 GB 5.9 GB
Fits Get file →
Q4_K_S2.2 GB 5.9 GB
Fits Get file →
Q4_K_M2.4 GB 6.1 GB
Fits Get file →
Q5_02.6 GB 6.4 GB
Fits Get file →
Q5_K_S2.6 GB 6.4 GB
Fits Get file →
Q5_K_M2.8 GB 6.5 GB
Fits Get file →
Q6_K3.1 GB 6.9 GB
Fits Get file →
Q8_04.1 GB 7.8 GB
Tight Get file →

For 8 GB VRAM, use IQ2_S (1.22 GB file, ~4.9 GB VRAM) or Q3_K_S (1.68 GB file, ~5.4 GB VRAM). If 12 GB VRAM is available, Q4_K_M (2.39 GB file, ~6.1 GB VRAM) offers higher precision. For the lowest memory, IQ1_S (0.84 GB file, ~4.6 GB VRAM) is recommended.

What GPU do you need for Borea Phi 3.5 Mini Instruct Jp?

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 Q4_K_S (2.2 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 7.8 GB in use).

Which Borea Phi 3.5 Mini Instruct Jp quant should you choose?

Q4_K_M is the usual starting point for Borea Phi 3.5 Mini Instruct Jp: it balances file size and quality well. Here it is a 2.4 GB file.

The Q8_0 file is 4.1 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 0.8 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

Architecturephi3
Parameters3.82B
Layers32
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bymmnga
FamilyPhi
Licensemit
Downloads (HF)2,443
Last updated2024-08-21

Frequently asked questions about Borea Phi 3.5 Mini Instruct Jp

How much VRAM does Borea Phi 3.5 Mini Instruct Jp need?

About 6.1 GB at Q4_K_M with an 8K context window. That is the 2.4 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 Borea Phi 3.5 Mini Instruct Jp on an 8 GB GPU?

Yes, with Q8_0: the 4.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Borea Phi 3.5 Mini Instruct Jp GGUF?

It depends on the quant: IQ1_S is 0.8 GB, IQ1_M is 0.9 GB, IQ2_XXS is 1.0 GB, IQ2_XS is 1.2 GB, IQ2_S is 1.2 GB, IQ2_M is 1.3 GB and 18 more.

What context length does Borea Phi 3.5 Mini Instruct Jp support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download Borea Phi 3.5 Mini Instruct Jp GGUF?

The files are on Hugging Face in the mmnga/HODACHI-Borea-Phi-3.5-mini-Instruct-Jp-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 Borea Phi 3.5 Mini Instruct Jp 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 Borea Phi 3.5 Mini Instruct Jp on 8 GB VRAM?

Yes, quantizations IQ1_S, IQ1_M, IQ2_XXS, IQ2_XS, IQ2_S, IQ2_M, Q2_K, IQ3_XXS, IQ3_XS, Q3_K_S, IQ3_S, IQ3_M, Q3_K_M, IQ4_XS, Q3_K_L, Q4_0, IQ4_NL, Q4_K_S, Q4_K_M, Q5_0, Q5_K_S, Q5_K_M, Q6_K, Q8_0 are available; IQ2_S and Q3_K_S are recommended for 8 GB VRAM.

What is the context length of this model?

The model supports 131072 tokens of context.

Is this model licensed for commercial use?

Yes, it is released under the MIT license, allowing commercial use.

Similar models

Browse all →

More from mmnga

All by mmnga →

More Phi models

All Phi →

Other small models

All small models →