PA

janhq_pandora-v1-10.7b

PandoraGGUF by TheBlokeUpdated 2023-12-14
Download on Hugging Face
Parameters10.7B
Context32K
Layers48
Architecturellama
Smallest quant4.5 GB
Quick answer

janhq_pandora-v1-10.7b needs about 8.6 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 4.5 GB (Q2_K) to 11.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Pandora‑v1 10.7B – a 10.7B‑parameter Llama‑style model in GGUF format

Pandora‑v1 10.7B is a 10.7‑billion‑parameter Llama‑based model. It is available in multiple quantizations and supports a 32,768‑token context window. The model is released under the Apache‑2.0 license and is fully offline compatible with llama.cpp and other GGUF clients.

Good at

  • Large context handling
  • Versatile quantization options
  • Open‑source offline use

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • No explicit language support listed

Best for

  • Chat applications needing long context
  • Local inference on moderate GPUs
  • Educational demos of large LLMs

Who it’s for. Developers and researchers who need a large Llama‑style model that can run locally. The model is suitable for those building offline chat systems or experimenting with different quantization levels.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.5 GB 6.7 GB
Fits Get file →
Q3_K_S4.7 GB 6.8 GB
Fits Get file →
Q3_K_M5.2 GB 7.3 GB
Tight Get file →
Q3_K_L5.7 GB 7.8 GB
Tight Get file →
Q4_06.1 GB 8.2 GB
Too big Get file →
Q4_K_S6.1 GB 8.2 GB
Too big Get file →
Q4_K_M6.5 GB 8.6 GB
Too big Get file →
Q5_07.4 GB 9.5 GB
Too big Get file →
Q5_K_S7.4 GB 9.5 GB
Too big Get file →
Q5_K_M7.6 GB 9.7 GB
Too big Get file →
Q6_K8.8 GB 10.9 GB
Too big Get file →
Q8_011.4 GB 13.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (6.46 GB file, ~8.6 GB VRAM). For 12 GB VRAM, Q5_K_M (7.6 GB file, ~9.7 GB VRAM). For 16 GB VRAM or more, Q6_K (8.81 GB file, ~10.9 GB VRAM) or Q8_0 (11.41 GB file, ~13.5 GB VRAM).

What GPU do you need for janhq_pandora-v1-10.7b?

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 Q3_K_L (5.7 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.8 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 13.5 GB in use).

Which janhq_pandora-v1-10.7b quant should you choose?

Q4_K_M is the usual starting point for janhq_pandora-v1-10.7b: it balances file size and quality well. Here it is a 6.5 GB file.

The Q8_0 file is 11.4 GB, about 1.8 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 4.5 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

Architecturellama
Parameters10.7B
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized byTheBloke
FamilyPandora
Licenseapache-2.0
Downloads (HF)1,294
Last updated2023-12-14

Frequently asked questions about janhq_pandora-v1-10.7b

How much VRAM does janhq_pandora-v1-10.7b need?

About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.5 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 janhq_pandora-v1-10.7b on an 8 GB GPU?

Yes, with Q3_K_L: the 5.7 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 janhq_pandora-v1-10.7b GGUF?

It depends on the quant: Q2_K is 4.5 GB, Q3_K_S is 4.7 GB, Q3_K_M is 5.2 GB, Q3_K_L is 5.7 GB, Q4_0 is 6.1 GB, Q4_K_S is 6.1 GB and 6 more.

What context length does janhq_pandora-v1-10.7b support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download janhq_pandora-v1-10.7b GGUF?

The files are on Hugging Face in the TheBloke/Pandora-v1-10.7B-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 janhq_pandora-v1-10.7b use?

Hugging Face lists the license as apache-2.0. 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_K_M quantization requires about 8.6 GB VRAM, which fits within an 8 GB GPU with some headroom.

Does this model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Pandora models

All Pandora →

Other medium models

All medium models →