NO

NovelAI-LM-3B-508k

NovelaiGGUF by NovelAIUpdated 2026-09-29
Download on Hugging Face
Parameters3.04B
Context2K
Layers28
Architecturestablelm
Smallest quant1.7 GB
Quick answer

NovelAI-LM-3B-508k needs about 5.1 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 6 quants, from 1.7 GB (IQ4_XS) to 6.1 GB (BF16).

NovelAI-LM-3B-508k – a 3.04B parameter stablelm model

NovelAI-LM-3B-508k is a 3.04B parameter stablelm model trained on a 2048 token context. It is the base model for Clio and is not specifically fine‑tuned for storytelling. The model is available in GGUF format and can be run with llama.cpp.

Good at

  • General language tasks
  • Baseline for fine‑tuning
  • Stablelm architecture

Limits

  • No vision support
  • GPL‑2.0 license
  • Context limited to 2048 tokens

Best for

  • Fine‑tuning custom chatbots
  • Research on stablelm models
  • Building lightweight LLM applications

Who it’s for. Developers and researchers who need a stablelm base model for custom fine‑tuning or experimentation. The GPL‑2.0 license requires open‑source compliance.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS1.7 GB 2.8 GB
Fits Get file →
Q4_K_M2.0 GB 3.1 GB
Fits Get file →
Q5_K_M2.3 GB 3.4 GB
Fits Get file →
Q6_K2.6 GB 3.8 GB
Fits Get file →
Q8_03.2 GB 4.4 GB
Fits Get file →
BF166.1 GB 7.2 GB
Tight Get file →

For 8 GB VRAM, use IQ4_XS (1.69 GB, ~4.8 GB memory) or Q4_K_M (1.98 GB, ~5.1 GB memory). If 12 GB VRAM is available, Q5_K_M (2.26 GB, ~5.3 GB memory) or Q6_K (2.64 GB, ~5.7 GB memory) are suitable. Larger quants require more memory.

What GPU do you need for NovelAI-LM-3B-508k?

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: the best quant that fits is Q6_K (2.6 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 6.3 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (6.1 GB file, about 9.2 GB in use).

Which NovelAI-LM-3B-508k quant should you choose?

Q4_K_M is the usual starting point for NovelAI-LM-3B-508k: it balances file size and quality well. Here it is a 2.0 GB file.

The Q8_0 file is 3.2 GB, about 1.6 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 IQ4_XS at 1.7 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestablelm
Parameters3.04B
Layers28
Trained context2,048 tokens
KV cache (fp16)308 KB per token

Source

Quantized byNovelAI
FamilyNovelai
Licensegpl-2.0
Downloads (HF)898
Last updated2026-09-29

Frequently asked questions about NovelAI-LM-3B-508k

How much VRAM does NovelAI-LM-3B-508k need?

About 5.1 GB at Q4_K_M with an 8K context window. That is the 2.0 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 NovelAI-LM-3B-508k on an 8 GB GPU?

Yes, with Q8_0: the 3.2 GB file needs about 6.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of NovelAI-LM-3B-508k GGUF?

It depends on the quant: IQ4_XS is 1.7 GB, Q4_K_M is 2.0 GB, Q5_K_M is 2.3 GB, Q6_K is 2.6 GB, Q8_0 is 3.2 GB, BF16 is 6.1 GB.

What context length does NovelAI-LM-3B-508k support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.6 GB at 8K and 0.6 GB at 2K.

Where can I download NovelAI-LM-3B-508k GGUF?

The files are on Hugging Face in the NovelAI/novelai-lm-3b-508k repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does NovelAI-LM-3B-508k use?

Hugging Face lists the license as gpl-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 NovelAI-LM-3B-508k on 8 GB VRAM?

Yes, the IQ4_XS quant uses 1.69 GB and requires about 4.8 GB VRAM at 8k context. Q4_K_M also fits within 8 GB VRAM.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under GPL‑2.0, requiring open‑source compliance.

Similar models

Browse all →

More from NovelAI

All by NovelAI →

More Novelai models

All Novelai →

Other tiny models

All tiny models →