NE

Nekomata 14b

NekomataGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters14.2B
Context8K
Layers40
Architectureqwen
Smallest quant4.4 GB
Quick answer

Nekomata 14b needs about 16.7 GB of memory at Q4_K_M (a 9.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 4.4 GB (IQ1_S) to 12.3 GB (Q6_K).

Nekomata 14b – 14.2B parameter Qwen-based Japanese‑English model

Nekomata 14b is a 14.2B parameter transformer trained on 66B tokens of Japanese and English data. It supports a maximum context length of 8192 tokens and is available in multiple GGUF quantizations.

Good at

  • Japanese language tasks
  • English language tasks
  • Long‑context generation

Limits

  • No vision support
  • License type is other
  • Requires GPU for efficient inference

Best for

  • Chatbots needing Japanese support
  • Content generation with long context
  • Fine‑tuning on Japanese corpora

Who it’s for. Developers building Japanese‑English language applications who need a large‑scale model with long context capability. The model is suitable for research and production use where GPU resources are available.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.4 GB 11.6 GB
Too big Get file →
IQ1_M4.6 GB 11.8 GB
Too big Get file →
IQ2_XXS4.9 GB 12.1 GB
Too big Get file →
IQ2_XS5.2 GB 12.4 GB
Too big Get file →
IQ2_S5.4 GB 12.7 GB
Too big Get file →
IQ2_M5.7 GB 12.9 GB
Too big Get file →
Q2_K5.8 GB 13.0 GB
Too big Get file →
IQ3_XXS6.3 GB 13.5 GB
Too big Get file →
IQ3_XS6.6 GB 13.8 GB
Too big Get file →
IQ3_S6.8 GB 14.0 GB
Too big Get file →
Q3_K_S6.8 GB 14.0 GB
Too big Get file →
IQ3_M7.4 GB 14.6 GB
Too big Get file →
Q3_K_M7.7 GB 14.9 GB
Too big Get file →
IQ4_XS7.8 GB 15.1 GB
Too big Get file →
Q3_K_L8.0 GB 15.2 GB
Too big Get file →
Q4_08.2 GB 15.4 GB
Too big Get file →
Q4_K_S8.6 GB 15.8 GB
Too big Get file →
Q4_K_M9.4 GB 16.7 GB
Too big Get file →
Q5_K_S10.0 GB 17.2 GB
Too big Get file →
Q5_K_M10.9 GB 18.1 GB
Too big Get file →
Q6_K12.3 GB 19.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (4.36 GB) or IQ1_M (4.56 GB). For 12 GB VRAM, IQ2_S (5.44 GB) or Q2_K (5.81 GB) are suitable. For 16 GB VRAM, Q4_K_M (9.45 GB) or Q5_K_S (10.03 GB) provide higher quality. Estimates are approximate.

What GPU do you need for Nekomata 14b?

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: the best quant that fits is IQ1_M (4.6 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (8.6 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (12.3 GB file, about 19.5 GB in use).

Which Nekomata 14b quant should you choose?

Q4_K_M is the usual starting point for Nekomata 14b: it balances file size and quality well. Here it is a 9.4 GB file.

If memory is tight, the smallest file is IQ1_S at 4.4 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

Architectureqwen
Parameters14.2B
Layers40
Trained context8,192 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymradermacher
FamilyNekomata
Licenseother
Downloads (HF)923
Last updated2024-08-02

Frequently asked questions about Nekomata 14b

How much VRAM does Nekomata 14b need?

About 16.7 GB at Q4_K_M with an 8K context window. That is the 9.4 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 Nekomata 14b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nekomata 14b GGUF?

It depends on the quant: IQ1_S is 4.4 GB, IQ1_M is 4.6 GB, IQ2_XXS is 4.9 GB, IQ2_XS is 5.2 GB, IQ2_S is 5.4 GB, IQ2_M is 5.7 GB and 15 more.

What context length does Nekomata 14b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 6.7 GB at 8K and 6.7 GB at 8K.

Where can I download Nekomata 14b GGUF?

The files are on Hugging Face in the mradermacher/nekomata-14b-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 Nekomata 14b 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 Nekomata 14b on 8 GB VRAM?

Yes, use the IQ1_S or IQ1_M quantization, which are 4.36 GB and 4.56 GB respectively.

Does the model support vision tasks?

No, the model has no vision capabilities.

What is the maximum context length?

The model supports a maximum context length of 8192 tokens.

Other GGUFs of nekomata-14b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Nekomata models

All Nekomata →

Other medium models

All medium models →