JA

japanese stablelm base beta 70B

JapaneseGGUF by TheBlokeUpdated 2023-11-06
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant29.3 GB
Quick answer

japanese stablelm base beta 70B needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 29.3 GB (Q2_K) to 48.8 GB (Q5_K_M).

Japanese StableLM Base Beta 70B – 70B‑parameter Llama‑2‑based language model

Japanese StableLM Base Beta 70B is a 70‑parameter decoder‑only model built on Llama‑2. It is fine‑tuned on Japanese data and supports Japanese language tasks. The model is released under the Llama2 Community License.

Good at

  • Japanese text generation
  • Fine‑tuning foundation
  • Instruction following (instruct variant)

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License allows commercial use but caution advised for harmful content

Best for

  • Japanese content creation
  • Fine‑tuning Japanese applications
  • Research on Japanese language models

Who it’s for. Developers and researchers needing a large Japanese language model for fine‑tuning or inference. The model can be used in commercial products under the Llama2 Community License, with caution regarding potential bias.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K29.3 GB 31.1 GB
Too big Get file →
Q3_K_S29.9 GB 31.8 GB
Too big Get file →
Q3_K_M33.2 GB 35.0 GB
Too big Get file →
Q3_K_L36.1 GB 38.0 GB
Too big Get file →
Q4_038.9 GB 40.7 GB
Too big Get file →
Q4_K_S39.1 GB 40.9 GB
Too big Get file →
Q4_K_M41.4 GB 43.3 GB
Too big Get file →
Q5_047.5 GB 49.3 GB
Too big Get file →
Q5_K_S47.5 GB 49.3 GB
Too big Get file →
Q5_K_M48.8 GB 50.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 39.07 GB, estimated memory 42.3 GB at 8 k context). For 12 GB VRAM, Q4_K_M (41.42 GB, 44.6 GB). For 16 GB VRAM, Q5_K_M (48.75 GB, 51.9 GB). Estimates are approximate.

What GPU do you need for japanese stablelm base beta 70B?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which japanese stablelm base beta 70B quant should you choose?

Q4_K_M is the usual starting point for japanese stablelm base beta 70B: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q2_K at 29.3 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
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byTheBloke
FamilyJapanese
Licensellama2
Downloads (HF)2,395
Last updated2023-11-06

Frequently asked questions about japanese stablelm base beta 70B

How much VRAM does japanese stablelm base beta 70B need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 japanese stablelm base beta 70B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of japanese stablelm base beta 70B GGUF?

It depends on the quant: Q2_K is 29.3 GB, Q3_K_S is 29.9 GB, Q3_K_M is 33.2 GB, Q3_K_L is 36.1 GB, Q4_0 is 38.9 GB, Q4_K_S is 39.1 GB and 4 more.

What context length does japanese stablelm base beta 70B 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 base beta 70B GGUF?

The files are on Hugging Face in the TheBloke/japanese-stablelm-base-beta-70B-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 base beta 70B use?

Hugging Face lists the license as llama2. 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?

Use the Q4_K_S quantised file; it requires about 42.3 GB of VRAM at 8 k context, so 8 GB is insufficient. Consider a lower‑bit quant or a smaller model.

What license does this model use?

The model is released under the Llama2 Community License, allowing commercial use with standard restrictions.

Does the model support vision tasks?

No, the model is a language model only and does not support vision inputs.

Other GGUFs of japanese-stablelm-base-beta-70b

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Japanese models

All Japanese →

Other large models

All large models →