TA

Tanuki 8B Dpo v1.0

TanukiGGUF by team-hatakeyama-phase2Updated 2024-12-22
Download on Hugging Face
Parameters7.51B
Context8K
Layers32
Architecturellama
Smallest quant1.8 GB
Quick answer

Tanuki 8B Dpo v1.0 needs about 6.1 GB of memory at Q4_K_M (a 4.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 1.8 GB (IQ1_S) to 15.0 GB (F16).

Tanuki 8B Dpo v1.0 – 7.51B‑parameter Japanese‑focused LLM

Tanuki 8B Dpo v1.0 is a 7.51B‑parameter llama architecture model trained on ~1.3T tokens. It is fine‑tuned with SFT and DPO for dialogue. The model supports 8192 context tokens and is released under apache‑2.0.

Good at

  • Japanese dialogue
  • Fine‑tuned instruction following
  • Large context handling

Limits

  • No vision support
  • Requires 8192 token context
  • GGUF quantization may reduce performance

Best for

  • Chatbot development
  • Japanese text generation
  • Research prototyping

Who it’s for. Developers building Japanese‑centric chat applications or researchers needing a large‑parameter llama model. The model is suitable for environments with sufficient VRAM and RAM to accommodate the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.8 GB 3.3 GB
Fits Get file →
IQ1_M1.9 GB 3.5 GB
Fits Get file →
IQ2_XXS2.1 GB 3.7 GB
Fits Get file →
IQ2_XS2.3 GB 3.9 GB
Fits Get file →
IQ2_S2.5 GB 4.0 GB
Fits Get file →
IQ2_M2.7 GB 4.2 GB
Fits Get file →
Q2_K_S2.7 GB 4.3 GB
Fits Get file →
Q2_K2.9 GB 4.4 GB
Fits Get file →
IQ3_XXS3.0 GB 4.6 GB
Fits Get file →
IQ3_XS3.2 GB 4.8 GB
Fits Get file →
Q3_K_S3.3 GB 4.9 GB
Fits Get file →
IQ3_S3.4 GB 4.9 GB
Fits Get file →
IQ3_M3.5 GB 5.0 GB
Fits Get file →
Q3_K_M3.7 GB 5.3 GB
Fits Get file →
Q3_K_L4.0 GB 5.6 GB
Fits Get file →
IQ4_XS4.1 GB 5.7 GB
Fits Get file →
IQ4_NL4.3 GB 5.9 GB
Fits Get file →
Q4_K_S4.3 GB 5.9 GB
Fits Get file →
Q4_K_M4.6 GB 6.1 GB
Fits Get file →
Q5_K_S5.2 GB 6.8 GB
Fits Get file →
Q5_K_M5.3 GB 6.9 GB
Fits Get file →
Q6_K6.2 GB 7.7 GB
Tight Get file →
Q8_08.0 GB 9.6 GB
Too big Get file →
F1615.0 GB 16.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (1.75 GB, 3.3 GB memory) or IQ1_M (1.89 GB, 3.5 GB memory). For 16 GB VRAM, Q4_K_M (4.56 GB, 6.1 GB memory) or Q5_K_M (5.34 GB, 6.9 GB memory) are recommended. Higher precision models like F16 (15.03 GB, 16.6 GB memory) require more VRAM.

What GPU do you need for Tanuki 8B Dpo v1.0?

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_S (2.5 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_S (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.2 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.6 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.0 GB file, about 16.6 GB in use).

Which Tanuki 8B Dpo v1.0 quant should you choose?

Q4_K_M is the usual starting point for Tanuki 8B Dpo v1.0: it balances file size and quality well. Here it is a 4.6 GB file.

The Q8_0 file is 8.0 GB, about 1.8 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 1.8 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

Architecturellama
Parameters7.51B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

FamilyTanuki
Licenseapache-2.0
Downloads (HF)1,060
Last updated2024-12-22

Frequently asked questions about Tanuki 8B Dpo v1.0

How much VRAM does Tanuki 8B Dpo v1.0 need?

About 6.1 GB at Q4_K_M with an 8K context window. That is the 4.6 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 Tanuki 8B Dpo v1.0 on an 8 GB GPU?

Yes, with Q6_K: the 6.2 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Tanuki 8B Dpo v1.0 GGUF?

It depends on the quant: IQ1_S is 1.8 GB, IQ1_M is 1.9 GB, IQ2_XXS is 2.1 GB, IQ2_XS is 2.3 GB, IQ2_S is 2.5 GB, IQ2_M is 2.7 GB and 18 more.

What context length does Tanuki 8B Dpo v1.0 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download Tanuki 8B Dpo v1.0 GGUF?

The files are on Hugging Face in the team-hatakeyama-phase2/Tanuki-8B-dpo-v1.0-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 Tanuki 8B Dpo v1.0 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 Tanuki 8B Dpo v1.0 on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quantizations, which estimate 3.3–3.5 GB memory at 8192 context.

Does the model support image inputs?

No, the model has no vision capabilities.

Is the GGUF version fully compatible with the original tokenizer?

The GGUF tokenizer may not be fully converted, potentially causing performance drops; other quantization formats are recommended.

Similar models

Browse all →

More from team-hatakeyama-phase2

All by team-hatakeyama-phase2 →

More Tanuki models

All Tanuki →

Other small models

All small models →