NE

Nekomata 14b Instruction

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

Nekomata 14b Instruction 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).

14.2B parameter instruction-tuned Qwen model

Nekomata 14b Instruction is a 14.2B parameter Qwen architecture model fine‑tuned on instruction data. It supports a 8192 token context window and follows the Alpaca input format.

Good at

  • Instruction following
  • Japanese language support
  • Translation tasks

Limits

  • No vision support
  • Requires GPU for efficient use
  • License is other

Best for

  • Chatbots needing Japanese instructions
  • Translation services
  • Code generation in Japanese

Who it’s for. Developers building Japanese‑centric LLM applications or researchers needing a large instruction‑tuned model. The model is suitable for environments with GPU resources and a need for 8192 token context.

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 file, 11.6 GB memory). For 12 GB VRAM, IQ2_M (5.71 GB file, 12.9 GB memory). For 16 GB VRAM, Q4_K_M (9.45 GB file, 16.7 GB memory). Estimates are approximate.

What GPU do you need for Nekomata 14b Instruction?

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 Instruction quant should you choose?

Q4_K_M is the usual starting point for Nekomata 14b Instruction: 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)2,037
Last updated2024-08-02

Frequently asked questions about Nekomata 14b Instruction

How much VRAM does Nekomata 14b Instruction 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 Instruction 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 Instruction 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 Instruction 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 Instruction GGUF?

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

Use the IQ1_S quant, which requires about 11.6 GB memory at 8k context. 8 GB VRAM may be insufficient for full inference.

Does the model support image inputs?

No, the model has no vision capabilities.

What is the context length of this model?

The model supports up to 8192 tokens of context.

Other GGUFs of nekomata-14b-instruction

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Nekomata models

All Nekomata →

Other medium models

All medium models →