NE

Nekomata 7b

NekomataGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters7.72B
Context32K
Layers32
Architectureqwen
Smallest quant2.0 GB
Quick answer

Nekomata 7b needs about 9.7 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 2.0 GB (IQ1_S) to 6.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

Nekomata 7b – a 7.72B Qwen‑based Japanese‑English LLM

Nekomata 7b is a 32‑layer, 4096‑hidden transformer trained on 30B tokens of Japanese and English data. It supports a maximum context length of 32768 tokens and is available in multiple GGUF quantizations.

Good at

  • Japanese text generation
  • English‑Japanese bilingual tasks
  • Long‑context handling

Limits

  • No vision support
  • License is other
  • No mixture of experts

Best for

  • Chatbots needing Japanese support
  • Long‑form content creation
  • Code generation in Japanese

Who it’s for. Developers building Japanese‑English applications who need a large language model that can run locally with GGUF. The model is suitable for users with GPU memory to load the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.0 GB 6.8 GB
Fits Get file →
IQ1_M2.1 GB 6.9 GB
Fits Get file →
IQ2_XXS2.3 GB 7.1 GB
Fits Get file →
IQ2_XS2.5 GB 7.3 GB
Tight Get file →
IQ2_S2.7 GB 7.5 GB
Tight Get file →
IQ2_M2.9 GB 7.7 GB
Tight Get file →
Q2_K3.0 GB 7.8 GB
Tight Get file →
IQ3_XXS3.2 GB 8.0 GB
Too big Get file →
IQ3_XS3.5 GB 8.3 GB
Too big Get file →
IQ3_S3.6 GB 8.4 GB
Too big Get file →
Q3_K_S3.6 GB 8.4 GB
Too big Get file →
IQ3_M3.9 GB 8.7 GB
Too big Get file →
Q3_K_M4.1 GB 8.9 GB
Too big Get file →
IQ4_XS4.3 GB 9.1 GB
Too big Get file →
Q3_K_L4.3 GB 9.1 GB
Too big Get file →
Q4_04.5 GB 9.3 GB
Too big Get file →
Q4_K_S4.5 GB 9.3 GB
Too big Get file →
Q4_K_M4.9 GB 9.7 GB
Too big Get file →
Q5_K_S5.4 GB 10.2 GB
Too big Get file →
Q5_K_M5.7 GB 10.5 GB
Too big Get file →
Q6_K6.3 GB 11.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (1.96 GB, 6.8 GB memory) or IQ1_M (2.1 GB, 6.9 GB). For 12 GB VRAM, IQ2_S (2.68 GB, 7.5 GB) or Q2_K (3.05 GB, 7.8 GB) are good choices. Higher memory allows Q4_K_M (4.9 GB, 9.7 GB) or Q5_K_M (5.71 GB, 10.5 GB).

What GPU do you need for Nekomata 7b?

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: the best quant that fits is IQ3_XXS (3.2 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 11.1 GB in use).

Which Nekomata 7b quant should you choose?

Q4_K_M is the usual starting point for Nekomata 7b: it balances file size and quality well. Here it is a 4.9 GB file.

If memory is tight, the smallest file is IQ1_S at 2.0 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
Parameters7.72B
Layers32
Trained context32,768 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyNekomata
Licenseother
Downloads (HF)1,164
Last updated2024-08-02

Frequently asked questions about Nekomata 7b

How much VRAM does Nekomata 7b need?

About 9.7 GB at Q4_K_M with an 8K context window. That is the 4.9 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 7b on an 8 GB GPU?

Yes, with IQ3_XXS: the 3.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nekomata 7b GGUF?

It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.1 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.7 GB, IQ2_M is 2.9 GB and 15 more.

What context length does Nekomata 7b support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download Nekomata 7b GGUF?

The files are on Hugging Face in the mradermacher/nekomata-7b-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 7b 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 7b on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quantizations will fit within 8 GB VRAM with an estimated 6.8–6.9 GB memory usage.

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 32768 tokens.

Other GGUFs of nekomata-7b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Nekomata models

All Nekomata →

Other small models

All small models →