LL

archangel_sft-kto_llama30b

LlamaGGUF by mradermacherUpdated 2024-05-31
Download on Hugging Face
Parameters32.5B
Context2K
Layers60
Architecturellama
Smallest quant12.0 GB
Quick answer

archangel_sft-kto_llama30b 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 14 quants, from 12.0 GB (Q2_K) to 34.6 GB (Q8_0).

Archangel SFT-KTO Llama30B – 32.5B parameter Llama model

Archangel SFT-KTO Llama30B is a 32.5B parameter Llama model trained with SFT+KTO loss and aligned on SHP, Anthropic HH and Open Assistant data. It supports 2048 token context and is released under Apache‑2.0.

Good at

  • Large context handling
  • High‑parameter Llama architecture
  • Fine‑tuned alignment

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is Apache‑2.0

Best for

  • Research on large‑scale LLMs
  • Fine‑tuning for specialized tasks
  • Benchmarking quantization effects

Who it’s for. Researchers and developers needing a high‑parameter Llama model with fine‑tuned alignment. Suitable for environments with sufficient GPU memory and a need for open‑source licensing.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.0 GB 15.8 GB
Too big Get file →
IQ3_XS13.3 GB 17.1 GB
Too big Get file →
IQ3_S14.1 GB 17.8 GB
Too big Get file →
Q3_K_S14.1 GB 17.8 GB
Too big Get file →
IQ3_M14.9 GB 18.7 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 →
IQ4_XS17.5 GB 21.2 GB
Too big Get file →
Q4_K_S18.5 GB 22.3 GB
Too big Get file →
Q4_K_M19.6 GB 23.4 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 Q2_K (12.05 GB, 25.6 GB memory at 8k context). For 16‑GB VRAM, Q4_K_M (19.62 GB, 33.2 GB memory) is a good balance. For 24‑GB VRAM, Q5_K_M (23.05 GB, 36.6 GB memory) offers higher quality.

What GPU do you need for archangel_sft-kto_llama30b?

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 IQ4_XS (17.5 GB file, about 31.1 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 archangel_sft-kto_llama30b quant should you choose?

Q4_K_M is the usual starting point for archangel_sft-kto_llama30b: 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 12.0 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

Architecturellama
Parameters32.5B
Layers60
Trained context2,048 tokens
KV cache (fp16)1560 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licenseapache-2.0
Downloads (HF)1,939
Last updated2024-05-31

Frequently asked questions about archangel_sft-kto_llama30b

How much VRAM does archangel_sft-kto_llama30b 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 archangel_sft-kto_llama30b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of archangel_sft-kto_llama30b GGUF?

It depends on the quant: Q2_K is 12.0 GB, IQ3_XS is 13.3 GB, IQ3_S is 14.1 GB, Q3_K_S is 14.1 GB, IQ3_M is 14.9 GB, Q3_K_M is 15.8 GB and 8 more.

What context length does archangel_sft-kto_llama30b 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 archangel_sft-kto_llama30b GGUF?

The files are on Hugging Face in the mradermacher/archangel_sft-kto_llama30b-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 archangel_sft-kto_llama30b 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 Archangel SFT‑KTO Llama30B on 8 GB VRAM?

Use the Q2_K quant, which is 12.05 GB and requires about 25.6 GB memory at 8k context. It will not fit in 8 GB VRAM, so a larger GPU is needed.

What is the context length of this model?

The model supports 2048 token context.

Is there a vision capability?

No, the model does not support vision.

Other GGUFs of archangel_sft-kto_llama30b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other medium models

All medium models →