ST

L3-8B-Stheno-v3.3-32K

SthenoGGUF by backyardaiUpdated 2024-06-26
Download on Hugging Face
Parameters8B
Context32K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

L3-8B-Stheno-v3.3-32K needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 21 quants, from 2.0 GB (IQ1_S) to 32.1 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

L3-8B-Stheno-v3.3-32K: 8B Llama model with 32K context

L3-8B-Stheno-v3.3-32K is an 8B llama model trained at 32768 tokens and expanded to 32K context with PoSE. It is designed for roleplay, RPGs, and storywriting. The model is uncensored during roleplay scenarios.

Good at

  • Roleplay and character interactions
  • Creative writing and RPG scenarios
  • Extended 32K context handling

Limits

  • No vision support
  • License is cc-by-nc-4.0
  • Requires quantisation for local use

Best for

  • One‑on‑one roleplay sessions
  • Long‑form story generation
  • Custom character development

Who it’s for. Developers and hobbyists who want a local, 32K context Llama model for roleplay and creative writing. The model runs with llama.cpp and GGUF quantisations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ1_M2.2 GB 3.7 GB
Fits Get file →
IQ2_XXS2.4 GB 4.0 GB
Fits Get file →
IQ2_XS2.6 GB 4.2 GB
Fits Get file →
IQ2_S2.8 GB 4.3 GB
Fits Get file →
IQ2_M2.9 GB 4.5 GB
Fits Get file →
IQ3_XXS3.3 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.4 GB 6.0 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
F3232.1 GB 33.7 GB
Too big Get file →

For 8 GB VRAM use IQ2_XS (2.61 GB) or Q4_K_S (4.69 GB). For 16 GB VRAM use Q4_K_M (4.92 GB) or Q5_K_S (5.6 GB). For 32 GB VRAM use Q6_K (6.6 GB) or Q8_0 (8.54 GB). Memory estimates are approximate.

What GPU do you need for L3-8B-Stheno-v3.3-32K?

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: the best quant that fits is IQ2_XXS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 48 GB VRAM: the best quant that fits is F32 (32.1 GB file, about 33.7 GB in use).

Which L3-8B-Stheno-v3.3-32K quant should you choose?

Q4_K_M is the usual starting point for L3-8B-Stheno-v3.3-32K: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 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 IQ1_S at 2.0 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
Parameters8B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bybackyardai
FamilyStheno
Downloads (HF)944
Last updated2024-06-26

Frequently asked questions about L3-8B-Stheno-v3.3-32K

How much VRAM does L3-8B-Stheno-v3.3-32K need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 L3-8B-Stheno-v3.3-32K on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 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 L3-8B-Stheno-v3.3-32K GGUF?

It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB, IQ2_M is 2.9 GB and 15 more.

What context length does L3-8B-Stheno-v3.3-32K support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download L3-8B-Stheno-v3.3-32K GGUF?

The files are on Hugging Face in the backyardai/L3-8B-Stheno-v3.3-32K-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 L3-8B-Stheno-v3.3-32K use?

Hugging Face lists the license as cc-by-nc-4.0. 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 L3-8B-Stheno-v3.3-32K on 8 GB VRAM?

Yes, using a quantisation such as IQ2_XS or Q4_K_S will fit within 8 GB VRAM with approximate memory usage of 4–6 GB.

Does the model support vision?

No, the model has no vision capabilities.

What license does the model use?

The model is licensed under cc‑by‑nc‑4.0, allowing non‑commercial use with attribution.

Other GGUFs of L3-8B-Stheno-v3.3-32K

Similar models

Browse all →

More from backyardai

All by backyardai →

More Stheno models

All Stheno →

Other small models

All small models →