LA

calderaai_30b-lazarus

LazarusGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters32.5B
Context2K
Layers60
Architecturellama
Smallest quant13.5 GB
Quick answer

calderaai_30b-lazarus needs about 33.2 GB of memory at Q4_K_M (a 19.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 13.5 GB (Q2_K) to 34.6 GB (Q8_0).

32.5B‑parameter LLaMA ensemble with LoRA merges

calderaai_30b-lazarus is a 32.5B‑parameter LLaMA‑based model created by Caldera AI. It combines multiple LoRA layers and model merges to enhance instruction following and storytelling. The model is available in GGUF format for llama.cpp and compatible clients.

Good at

  • Instruction following
  • Creative storytelling
  • Multi‑domain dialogue

Limits

  • No vision support
  • Requires 8k context for full capacity
  • License is other

Best for

  • Chatbots needing large context
  • Story generation
  • Research prototyping

Who it’s for. Users who need a large‑context LLaMA model with LoRA‑enhanced capabilities and have access to GPU or CPU inference tools that support GGUF. The model is suitable for developers building chat or storytelling applications.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K13.5 GB 17.3 GB
Too big Get file →
Q3_K_S14.1 GB 17.8 GB
Too big Get file →
Q3_K_M15.8 GB 19.5 GB
Too big Get file →
Q3_K_L17.3 GB 21.1 GB
Too big Get file →
Q4_018.4 GB 22.1 GB
Too big Get file →
Q4_K_S18.4 GB 22.2 GB
Too big Get file →
Q4_K_M19.6 GB 23.4 GB
Too big Get file →
Q5_022.4 GB 26.2 GB
Too big Get file →
Q5_K_S22.4 GB 26.2 GB
Too big Get file →
Q5_K_M23.0 GB 26.8 GB
Too big Get file →
Q6_K26.7 GB 30.5 GB
Too big Get file →
Q8_034.6 GB 38.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K (file size 18.36 GB, memory 31.9 GB at 8k context). For 12 GB VRAM, Q5_0 (22.4 GB, 36 GB). For 16 GB VRAM, Q6_K (26.69 GB, 40.3 GB). Estimates are approximate.

What GPU do you need for calderaai_30b-lazarus?

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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q4_K_S (18.4 GB file, about 32.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (26.7 GB file, about 40.3 GB in use).

Which calderaai_30b-lazarus quant should you choose?

Q4_K_M is the usual starting point for calderaai_30b-lazarus: it balances file size and quality well. Here it is a 19.6 GB file.

The Q8_0 file is 34.6 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 13.5 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
Parameters32.5B
Layers60
Trained context2,048 tokens
KV cache (fp16)1560 KB per token

Source

Quantized byTheBloke
FamilyLazarus
Licenseother
Downloads (HF)863
Last updated2023-09-27

Frequently asked questions about calderaai_30b-lazarus

How much VRAM does calderaai_30b-lazarus need?

About 33.2 GB at Q4_K_M with an 8K context window. That is the 19.6 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 calderaai_30b-lazarus on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 27.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of calderaai_30b-lazarus GGUF?

It depends on the quant: Q2_K is 13.5 GB, Q3_K_S is 14.1 GB, Q3_K_M is 15.8 GB, Q3_K_L is 17.3 GB, Q4_0 is 18.4 GB, Q4_K_S is 18.4 GB and 6 more.

What context length does calderaai_30b-lazarus support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 13.1 GB at 8K and 3.3 GB at 2K.

Where can I download calderaai_30b-lazarus GGUF?

The files are on Hugging Face in the TheBloke/30B-Lazarus-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 calderaai_30b-lazarus 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 calderaai_30b-lazarus on 8 GB VRAM?

Use the Q4_K quantized model; it requires about 31.9 GB of memory at 8k context, so 8 GB VRAM alone is insufficient without swapping.

Does the model support vision tasks?

No, the model has no vision capabilities.

What context length does it support?

It was trained on 2048 tokens and supports up to 8k context with the provided GGUF files.

Other GGUFs of 30B-Lazarus

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Lazarus models

All Lazarus →

Other medium models

All medium models →