NI

L3.1 Celestial Stone 2x8B

NiitamaGGUF by QuantFactoryUpdated 2024-09-15
Download on Hugging Face
Parameters13.7B
Context128K
Layers32
Architecturellama
Smallest quant5.2 GB
Quick answer

L3.1 Celestial Stone 2x8B needs about 9.9 GB of memory at Q4_K_M (a 8.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 5.2 GB (Q2_K) to 14.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

L3.1 Celestial Stone 2x8B – 13.7B Mixture of Experts Llama-3.1 model

L3.1 Celestial Stone 2x8B is a 13.7B parameter Llama-3.1 model with a 131072 token context window. It uses two experts in tandem for token generation and is quantized for efficient inference. The model is available in multiple GGUF quantizations.

Good at

  • Large context generation
  • Mixture of expert inference
  • Efficient quantized inference

Limits

  • No vision support
  • License not specified
  • No zero‑shot unethical question handling

Best for

  • Story writing prompts
  • SillyTavern style dialogue
  • Long‑form content generation

Who it’s for. Developers and researchers who need a large‑context Llama‑3.1 model with mixture‑of‑experts capabilities and can run GGUF files in llama.cpp. The model is suitable for applications that require extended context and efficient inference on GPU or CPU.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.2 GB 6.8 GB
Fits Get file →
Q3_K_S6.1 GB 7.7 GB
Tight Get file →
Q3_K_M6.7 GB 8.3 GB
Too big Get file →
Q3_K_L7.2 GB 8.8 GB
Too big Get file →
Q4_07.8 GB 9.4 GB
Too big Get file →
Q4_K_S7.9 GB 9.5 GB
Too big Get file →
Q4_K_M8.3 GB 9.9 GB
Too big Get file →
Q4_18.7 GB 10.2 GB
Too big Get file →
Q5_09.5 GB 11.0 GB
Too big Get file →
Q5_K_S9.5 GB 11.0 GB
Too big Get file →
Q5_K_M9.7 GB 11.3 GB
Too big Get file →
Q5_110.3 GB 11.9 GB
Too big Get file →
Q6_K11.2 GB 12.8 GB
Too big Get file →
Q8_014.5 GB 16.1 GB
Too big Get file →

For 8‑GB VRAM use Q4_K_M (file size 8.33 GB, estimated 9.9 GB memory). For 12‑GB VRAM use Q5_K_M (file size 9.73 GB, estimated 11.3 GB memory). For 16‑GB VRAM use Q6_K (file size 11.22 GB, estimated 12.8 GB memory).

What GPU do you need for L3.1 Celestial Stone 2x8B?

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: the best quant that fits is Q3_K_S (6.1 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_1 (10.3 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.2 GB file, about 12.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.5 GB file, about 16.1 GB in use).

Which L3.1 Celestial Stone 2x8B quant should you choose?

Q4_K_M is the usual starting point for L3.1 Celestial Stone 2x8B: it balances file size and quality well. Here it is a 8.3 GB file.

The Q8_0 file is 14.5 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 Q2_K at 5.2 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
Parameters13.7B (approximate, mixture of experts)
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byQuantFactory
FamilyNiitama
Downloads (HF)1,025
Last updated2024-09-15

Frequently asked questions about L3.1 Celestial Stone 2x8B

How much VRAM does L3.1 Celestial Stone 2x8B need?

About 9.9 GB at Q4_K_M with an 8K context window. That is the 8.3 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 L3.1 Celestial Stone 2x8B on an 8 GB GPU?

Yes, with Q3_K_S: the 6.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of L3.1 Celestial Stone 2x8B GGUF?

It depends on the quant: Q2_K is 5.2 GB, Q3_K_S is 6.1 GB, Q3_K_M is 6.7 GB, Q3_K_L is 7.2 GB, Q4_0 is 7.8 GB, Q4_K_S is 7.9 GB and 8 more.

What context length does L3.1 Celestial Stone 2x8B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 L3.1 Celestial Stone 2x8B GGUF?

The files are on Hugging Face in the QuantFactory/L3.1-Celestial-Stone-2x8B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run L3.1 Celestial Stone 2x8B on 8 GB VRAM?

Use the Q4_K_M quant; it requires about 9.9 GB memory at 8k context, which is close to 8 GB but may need swapping.

What is the maximum context length of this model?

The model supports a context length of 131072 tokens.

Does this model support vision inputs?

No, the model does not support vision inputs.

Other GGUFs of L3.1-8B-Niitama-v1.1

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Niitama models

All Niitama →

Other medium models

All medium models →