PU

PuddleJumper 13B

PuddlejumperGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

PuddleJumper 13B needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 5.4 GB (Q2_K) to 13.8 GB (Q8_0).

PuddleJumper 13B – a 13‑billion‑parameter llama model in GGUF format

PuddleJumper 13B is a 13‑billion‑parameter llama model released under the llama2 license. It supports a 4096‑token context window and is available in multiple GGUF quantisations. The model is suitable for chat and general-purpose language tasks.

Good at

  • Chat‑style interactions
  • General language generation
  • Prompt‑format flexibility

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • License is llama2

Best for

  • Local chat applications
  • Fine‑tuning on custom prompts
  • Embedding generation

Who it’s for. Developers and researchers who need a large llama model that can run locally with GGUF support. The model works well with llama.cpp, text‑generation‑webui, and other GGUF‑compatible tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 9.3 GB
Too big Get file →
Q3_K_S5.7 GB 9.5 GB
Too big Get file →
Q3_K_M6.3 GB 10.2 GB
Too big Get file →
Q3_K_L6.9 GB 10.8 GB
Too big Get file →
Q4_07.4 GB 11.2 GB
Too big Get file →
Q4_K_S7.4 GB 11.3 GB
Too big Get file →
Q4_K_M7.9 GB 11.7 GB
Too big Get file →
Q4_18.2 GB 12.0 GB
Too big Get file →
Q5_09.0 GB 12.8 GB
Too big Get file →
Q5_K_S9.0 GB 12.8 GB
Too big Get file →
Q5_K_M9.2 GB 13.1 GB
Too big Get file →
Q5_19.8 GB 13.6 GB
Too big Get file →
Q6_K10.7 GB 14.5 GB
Too big Get file →
Q8_013.8 GB 17.7 GB
Too big Get file →

For 8‑GB VRAM, use Q4_K_M (7.87 GB file, ~15.1 GB RAM). For 12‑GB VRAM, Q5_K_M (9.23 GB file, ~16.4 GB RAM). For 16‑GB VRAM, Q6_K (10.68 GB file, ~17.9 GB RAM). These estimates are approximate.

What GPU do you need for PuddleJumper 13B?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q4_1 (8.2 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).

Which PuddleJumper 13B quant should you choose?

Q4_K_M is the usual starting point for PuddleJumper 13B: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.8 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 5.4 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

Architecturellama
Parameters13B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTheBloke
Licensellama2
Downloads (HF)7,869
Last updated2023-09-27

Frequently asked questions about PuddleJumper 13B

How much VRAM does PuddleJumper 13B need?

About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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 PuddleJumper 13B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of PuddleJumper 13B GGUF?

It depends on the quant: Q2_K is 5.4 GB, Q3_K_S is 5.7 GB, Q3_K_M is 6.3 GB, Q3_K_L is 6.9 GB, Q4_0 is 7.4 GB, Q4_K_S is 7.4 GB and 8 more.

What context length does PuddleJumper 13B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download PuddleJumper 13B GGUF?

The files are on Hugging Face in the TheBloke/PuddleJumper-13B-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 PuddleJumper 13B use?

Hugging Face lists the license as llama2. 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 PuddleJumper 13B on 8 GB VRAM?

Use the Q4_K_M quantised model; it requires about 15.1 GB of RAM at 8‑k context, which is close to the VRAM limit.

Does PuddleJumper 13B support vision tasks?

No, the model has no vision capabilities.

What prompt format should I use?

The recommended format is Vicuna‑short with a system prompt; it also works with OpenOrca and Platypus formats.

Other GGUFs of PuddleJumper-13b

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Puddlejumper models

All Puddlejumper →

Other medium models

All medium models →