JA

Japanese Stablelm 3b 4e1t Instruct

JapaneseGGUF by mradermacherUpdated 2025-01-26
Download on Hugging Face
Parameters2.8B
Context4K
Layers32
Architecturestablelm
Smallest quant0.7 GB
Quick answer

Japanese Stablelm 3b 4e1t Instruct needs about 4.9 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 0.7 GB (IQ1_S) to 2.3 GB (Q6_K).

Japanese StableLM-3B-4E1T Instruct – 2.8B parameter decoder-only model

Japanese StableLM-3B-4E1T Instruct is a 2.8B parameter decoder-only language model fine‑tuned on instruction‑following datasets. It is built on the Japanese StableLM-3B-4E1T Base and supports Japanese text generation. The model is released under Apache License, Version 2.0.

Good at

  • Instruction following in Japanese
  • Japanese text generation
  • Fine‑tuning foundation

Limits

  • No vision support
  • Context length limited to 4096 tokens
  • Requires at least 3.9 GB VRAM for IQ1_S at 8 k context

Best for

  • Japanese chatbot development
  • Japanese content creation
  • Japanese data augmentation

Who it’s for. The model is intended for developers and researchers who need a Japanese language foundation model for application‑specific fine‑tuning. Commercial use is allowed under the Apache 2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.7 GB 2.5 GB
Fits Get file →
IQ1_M0.7 GB 2.6 GB
Fits Get file →
IQ2_XXS0.8 GB 2.7 GB
Fits Get file →
IQ2_XS0.9 GB 2.7 GB
Fits Get file →
IQ2_S0.9 GB 2.8 GB
Fits Get file →
Q2_K_S1.0 GB 2.8 GB
Fits Get file →
IQ2_M1.0 GB 2.9 GB
Fits Get file →
Q2_K1.1 GB 2.9 GB
Fits Get file →
IQ3_XXS1.1 GB 2.9 GB
Fits Get file →
IQ3_XS1.2 GB 3.0 GB
Fits Get file →
IQ3_S1.3 GB 3.1 GB
Fits Get file →
Q3_K_S1.3 GB 3.1 GB
Fits Get file →
IQ3_M1.3 GB 3.2 GB
Fits Get file →
Q3_K_M1.4 GB 3.2 GB
Fits Get file →
Q3_K_L1.5 GB 3.4 GB
Fits Get file →
IQ4_XS1.5 GB 3.4 GB
Fits Get file →
IQ4_NL1.6 GB 3.5 GB
Fits Get file →
Q4_01.6 GB 3.5 GB
Fits Get file →
Q4_K_S1.6 GB 3.5 GB
Fits Get file →
Q4_K_M1.7 GB 3.6 GB
Fits Get file →
Q4_11.8 GB 3.6 GB
Fits Get file →
Q5_K_S1.9 GB 3.8 GB
Fits Get file →
Q5_K_M2.0 GB 3.8 GB
Fits Get file →
Q6_K2.3 GB 4.1 GB
Fits Get file →

For 4 GB VRAM, use IQ2_XXS (0.81 GB file, 4 GB memory) or IQ2_XS (0.88 GB file, 4.1 GB memory). For 6 GB VRAM, Q4_K_M (1.71 GB file, 4.9 GB memory) or Q5_K_M (1.99 GB file, 5.2 GB memory) are suitable. Memory estimates are approximate.

What GPU do you need for Japanese Stablelm 3b 4e1t Instruct?

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: the best quant that fits is IQ2_XXS (0.8 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (2.3 GB file, about 5.5 GB in use).

Which Japanese Stablelm 3b 4e1t Instruct quant should you choose?

Q4_K_M is the usual starting point for Japanese Stablelm 3b 4e1t Instruct: it balances file size and quality well. Here it is a 1.7 GB file.

If memory is tight, the smallest file is IQ1_S at 0.7 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

Architecturestablelm
Parameters2.8B
Layers32
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyJapanese
Licenseapache-2.0
Downloads (HF)553
Last updated2025-01-26

Frequently asked questions about Japanese Stablelm 3b 4e1t Instruct

How much VRAM does Japanese Stablelm 3b 4e1t Instruct need?

About 4.9 GB at Q4_K_M with an 8K context window. That is the 1.7 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 Japanese Stablelm 3b 4e1t Instruct on an 8 GB GPU?

Yes, with Q6_K: the 2.3 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Japanese Stablelm 3b 4e1t Instruct GGUF?

It depends on the quant: IQ1_S is 0.7 GB, IQ1_M is 0.7 GB, IQ2_XXS is 0.8 GB, IQ2_XS is 0.9 GB, IQ2_S is 0.9 GB, Q2_K_S is 1.0 GB and 18 more.

What context length does Japanese Stablelm 3b 4e1t Instruct support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download Japanese Stablelm 3b 4e1t Instruct GGUF?

The files are on Hugging Face in the mradermacher/japanese-stablelm-3b-4e1t-instruct-i1-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 Japanese Stablelm 3b 4e1t Instruct 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 this model on 8 GB VRAM?

Yes, the largest quant (Q6_K) requires about 5.5 GB at 8 k context, so 8 GB VRAM is sufficient.

Does the model support vision tasks?

No, the model is a decoder‑only text model and has no vision support.

What license does the model use?

The model is released under Apache License, Version 2.0.

Other GGUFs of japanese-stablelm-3b-4e1t-instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Japanese models

All Japanese →

Other tiny models

All tiny models →