NE

Nekomata 7b Pfn Qfin

NekomataGGUF by RichardErkhovUpdated 2024-09-21
Download on Hugging Face
Parameters7.72B
Context32K
Layers32
Architectureqwen
Smallest quant3.0 GB
Quick answer

Nekomata 7b Pfn Qfin 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 22 quants, from 3.0 GB (Q2_K) to 8.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

Nekomata 7b Pfn Qfin – 7.72B parameter Japanese/English finance LLM

Nekomata 7b Pfn Qfin is a 7.72B parameter causal decoder-only model fine‑tuned on 370M tokens for finance. It supports Japanese and English and offers a 2048 token context window. The model is released under the Tongyi Qianwen license.

Good at

  • Finance text generation
  • Japanese and English support
  • Fine‑tuned for continuous sentences

Limits

  • No vision support
  • License restricts certain uses
  • Context limited to 2048 tokens

Best for

  • Financial report drafting
  • Bilingual finance content creation
  • Japanese‑English financial dialogue

Who it’s for. Developers needing a finance‑focused LLM that handles Japanese and English. Researchers working on financial language models may also find it useful.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.0 GB 7.8 GB
Tight 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_K4.1 GB 8.9 GB
Too big Get file →
Q3_K_M4.1 GB 8.9 GB
Too big Get file →
Q3_K_L4.3 GB 9.1 GB
Too big Get file →
IQ4_XS4.3 GB 9.1 GB
Too big Get file →
Q4_04.5 GB 9.3 GB
Too big Get file →
IQ4_NL4.5 GB 9.3 GB
Too big Get file →
Q4_K_S4.5 GB 9.3 GB
Too big Get file →
Q4_K4.9 GB 9.7 GB
Too big Get file →
Q4_K_M4.9 GB 9.7 GB
Too big Get file →
Q4_15.0 GB 9.8 GB
Too big Get file →
Q5_05.4 GB 10.2 GB
Too big Get file →
Q5_K_S5.4 GB 10.2 GB
Too big Get file →
Q5_K5.7 GB 10.5 GB
Too big Get file →
Q5_K_M5.7 GB 10.5 GB
Too big Get file →
Q5_15.8 GB 10.6 GB
Too big Get file →
Q6_K6.3 GB 11.1 GB
Too big Get file →
Q8_08.2 GB 13.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 4.51 GB, estimated 9.3 GB memory). If 12 GB VRAM is available, Q5_K (5.71 GB, 10.5 GB memory) offers higher quality. For 16 GB VRAM, Q6_K (6.34 GB, 11.1 GB memory) provides a balance between size and performance.

What GPU do you need for Nekomata 7b Pfn Qfin?

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 Q2_K (3.0 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.2 GB file, about 13.0 GB in use).

Which Nekomata 7b Pfn Qfin quant should you choose?

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

The Q8_0 file is 8.2 GB, about 1.7 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 Q2_K at 3.0 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 byRichardErkhov
FamilyNekomata
Licenseother
Downloads (HF)707
Last updated2024-09-21

Frequently asked questions about Nekomata 7b Pfn Qfin

How much VRAM does Nekomata 7b Pfn Qfin 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 Pfn Qfin on an 8 GB GPU?

Yes, with Q2_K: the 3.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nekomata 7b Pfn Qfin GGUF?

It depends on the quant: Q2_K is 3.0 GB, IQ3_XS is 3.5 GB, IQ3_S is 3.6 GB, Q3_K_S is 3.6 GB, IQ3_M is 3.9 GB, Q3_K is 4.1 GB and 16 more.

What context length does Nekomata 7b Pfn Qfin 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 Pfn Qfin GGUF?

The files are on Hugging Face in the RichardErkhov/pfnet_-_nekomata-7b-pfn-qfin-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 Pfn Qfin 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, the Q4_0 quantization requires about 9.3 GB memory at 8 k context, which fits within 8 GB VRAM with some overhead.

Does the model support image inputs?

No, this model does not have vision capabilities.

What context length does it support?

The model was fine‑tuned at 2048 tokens and supports up to that context length.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Nekomata models

All Nekomata →

Other small models

All small models →