KA

Karakuri Lm 70b Chat v0.1

KarakuriGGUF by mradermacherUpdated 2024-12-11
Download on Hugging Face
Parameters69.2B
Context4K
Layers80
Architecturellama
Smallest quant14.6 GB
Quick answer

Karakuri Lm 70b Chat v0.1 needs about 44.8 GB of memory at Q4_K_M (a 41.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 21 quants, from 14.6 GB (IQ1_S) to 48.9 GB (Q5_K_M).

Karakuri Lm 70b Chat v0.1 – a 69.2B parameter Japanese‑English causal decoder

Karakuri Lm 70b Chat v0.1 is a 69.2B parameter causal decoder‑only transformer. It builds on Llama 2 and is fine‑tuned with SteerLM and continual learning. The model supports English and Japanese and is available in multiple GGUF quantizations.

Good at

  • Japanese‑English conversational AI
  • Large context handling up to 4096 tokens
  • Fine‑tuned with SteerLM for balanced responses

Limits

  • No vision support
  • License type other – check usage terms
  • Requires 8k context for memory estimates

Best for

  • Chatbots needing Japanese support
  • Multilingual content generation
  • Research on fine‑tuned Llama 2 variants

Who it’s for. Developers and researchers who need a large Japanese‑English language model with fine‑tuned conversational capabilities. The model is suitable for applications that can run on GPU or CPU with sufficient VRAM and RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S14.6 GB 16.5 GB
Too big Get file →
IQ1_M16.1 GB 17.9 GB
Too big Get file →
IQ2_XXS18.4 GB 20.2 GB
Too big Get file →
IQ2_XS20.4 GB 22.3 GB
Too big Get file →
IQ2_S21.5 GB 23.3 GB
Too big Get file →
IQ2_M23.4 GB 25.2 GB
Too big Get file →
Q2_K_S23.7 GB 25.5 GB
Too big Get file →
Q2_K25.6 GB 27.4 GB
Too big Get file →
IQ3_XXS26.7 GB 28.5 GB
Too big Get file →
IQ3_XS28.5 GB 30.3 GB
Too big Get file →
IQ3_S30.1 GB 31.9 GB
Too big Get file →
Q3_K_S30.1 GB 31.9 GB
Too big Get file →
IQ3_M31.1 GB 32.9 GB
Too big Get file →
Q3_K_M33.4 GB 35.3 GB
Too big Get file →
Q3_K_L36.3 GB 38.1 GB
Too big Get file →
IQ4_XS37.0 GB 38.8 GB
Too big Get file →
Q4_039.2 GB 41.0 GB
Too big Get file →
Q4_K_S39.4 GB 41.2 GB
Too big Get file →
Q4_K_M41.6 GB 43.4 GB
Too big Get file →
Q5_K_S47.6 GB 49.5 GB
Too big Get file →
Q5_K_M48.9 GB 50.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (14.65 GB file, 17.8 GB memory at 8k context). For 12 GB VRAM, IQ2_S (21.48 GB file, 24.7 GB memory). For 16 GB VRAM, Q3_K_M (33.41 GB file, 36.6 GB memory). Estimates are approximate.

What GPU do you need for Karakuri Lm 70b Chat v0.1?

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: the best quant that fits is IQ2_XS (20.4 GB file, about 23.6 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XS (28.5 GB file, about 31.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.6 GB file, about 44.8 GB in use).

Which Karakuri Lm 70b Chat v0.1 quant should you choose?

Q4_K_M is the usual starting point for Karakuri Lm 70b Chat v0.1: it balances file size and quality well. Here it is a 41.6 GB file.

If memory is tight, the smallest file is IQ1_S at 14.6 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
Parameters69.2B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyKarakuri
Licenseother
Downloads (HF)782
Last updated2024-12-11

Frequently asked questions about Karakuri Lm 70b Chat v0.1

How much VRAM does Karakuri Lm 70b Chat v0.1 need?

About 44.8 GB at Q4_K_M with an 8K context window. That is the 41.6 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 Karakuri Lm 70b Chat v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Karakuri Lm 70b Chat v0.1 GGUF?

It depends on the quant: IQ1_S is 14.6 GB, IQ1_M is 16.1 GB, IQ2_XXS is 18.4 GB, IQ2_XS is 20.4 GB, IQ2_S is 21.5 GB, IQ2_M is 23.4 GB and 15 more.

What context length does Karakuri Lm 70b Chat v0.1 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 Karakuri Lm 70b Chat v0.1 GGUF?

The files are on Hugging Face in the mradermacher/karakuri-lm-70b-chat-v0.1-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 Karakuri Lm 70b Chat v0.1 use?

Hugging Face lists the license as other. 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, using the IQ1_S quantization which requires about 17.8 GB memory at 8k context. It will need a GPU with at least 8 GB VRAM and sufficient system RAM.

Does this model support vision tasks?

No, the model is a causal language model and does not include vision capabilities.

What context length does it support?

The model was trained with a context length of 4096 tokens, which is the maximum supported context.

Other GGUFs of karakuri-lm-70b-chat-v0.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Karakuri models

All Karakuri →

Other large models

All large models →