IN

Index-1.9B-Character_test

IndexGGUF by IndexTeamUpdated 2024-06-26
Download on Hugging Face
Parameters2.17B
Context4K
Layers36
Architecturellama
Smallest quant1.3 GB
Quick answer

Index-1.9B-Character_test needs about 4.2 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 1.3 GB (Q4_0) to 4.3 GB (F16).

Index-1.9B-Character_test – a 2.17B parameter llama model in GGUF format

Index-1.9B-Character_test is a 2.17B parameter llama architecture model. It is available in multiple quantizations for llama.cpp usage. The model supports a 4096 token context window.

Good at

  • Character roleplay
  • Text generation
  • Dialogue simulation

Limits

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

Best for

  • Chatbot development
  • Creative writing prompts
  • Game NPC dialogue

Who it’s for. Developers building lightweight LLM applications who need a small context model. The model is suitable for local deployment with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_01.3 GB 3.0 GB
Fits Get file →
Q4_K_M1.3 GB 3.0 GB
Fits Get file →
Q6_K1.8 GB 3.5 GB
Fits Get file →
Q8_02.3 GB 4.0 GB
Fits Get file →
F164.3 GB 6.1 GB
Fits Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_M (1.26 GB or 1.33 GB). For 12 GB VRAM, Q6_K (1.78 GB) or Q8_0 (2.31 GB) are suitable. For 16 GB VRAM, F16 (4.35 GB) provides higher precision.

What GPU do you need for Index-1.9B-Character_test?

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: the best quant that fits is Q8_0 (2.3 GB file, about 5.2 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (4.3 GB file, about 7.3 GB in use).

Which Index-1.9B-Character_test quant should you choose?

Q4_K_M is the usual starting point for Index-1.9B-Character_test: it balances file size and quality well. Here it is a 1.3 GB file.

The Q8_0 file is 2.3 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 Q4_0 at 1.3 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters2.17B
Layers36
Trained context4,096 tokens
KV cache (fp16)288 KB per token

Source

Quantized byIndexTeam
FamilyIndex
Licenseother
Downloads (HF)614
Last updated2024-06-26

Frequently asked questions about Index-1.9B-Character_test

How much VRAM does Index-1.9B-Character_test need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Index-1.9B-Character_test on an 8 GB GPU?

Yes, with F16: the 4.3 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Index-1.9B-Character_test GGUF?

It depends on the quant: Q4_0 is 1.3 GB, Q4_K_M is 1.3 GB, Q6_K is 1.8 GB, Q8_0 is 2.3 GB, F16 is 4.3 GB.

What context length does Index-1.9B-Character_test support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.4 GB at 8K and 1.2 GB at 4K.

Where can I download Index-1.9B-Character_test GGUF?

The files are on Hugging Face in the IndexTeam/Index-1.9B-Character-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 Index-1.9B-Character_test 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, Q4_0 and Q4_K_M quantizations fit within 8 GB VRAM with an estimated 4.2 GB memory usage at 8k context.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What is the context length of this model?

The model supports a 4096 token context window.

Similar models

Browse all →

More from IndexTeam

All by IndexTeam →

More Index models

All Index →

Other tiny models

All tiny models →