NY

L3-Nymeria-15B

NymeriaGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters15B
Context8K
Layers64
Architecturellama
Smallest quant3.5 GB
Quick answer

L3-Nymeria-15B needs about 11.8 GB of memory at Q4_K_M (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 3.5 GB (IQ1_S) to 12.3 GB (Q6_K).

15B parameter Llama model with multiple IQ and Q quantizations

L3-Nymeria-15B is a 15B‑parameter Llama architecture model trained on 8192 context tokens. It is available in a range of GGUF quantizations from IQ1_S to Q6_K. The model supports multiple languages and is suitable for general text generation tasks.

Good at

  • Large context handling
  • High parameter count
  • Wide quantization options

Limits

  • No vision support
  • License not specified
  • Requires 8k context for estimates

Best for

  • Chat applications
  • Text completion
  • Research prototyping

Who it’s for. Developers and researchers needing a large Llama model with flexible quantization. The model is ideal for those who can manage the memory requirements of a 15B parameter network.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.5 GB 6.1 GB
Fits Get file →
IQ1_M3.8 GB 6.4 GB
Fits Get file →
IQ2_XXS4.3 GB 6.9 GB
Fits Get file →
IQ2_XS4.7 GB 7.3 GB
Tight Get file →
IQ2_S4.9 GB 7.6 GB
Tight Get file →
IQ2_M5.3 GB 7.9 GB
Tight Get file →
Q2_K5.7 GB 8.4 GB
Too big Get file →
IQ3_XXS6.0 GB 8.6 GB
Too big Get file →
IQ3_XS6.4 GB 9.0 GB
Too big Get file →
Q3_K_S6.7 GB 9.3 GB
Too big Get file →
IQ3_S6.7 GB 9.3 GB
Too big Get file →
IQ3_M6.9 GB 9.6 GB
Too big Get file →
Q3_K_M7.4 GB 10.0 GB
Too big Get file →
Q3_K_L8.0 GB 10.6 GB
Too big Get file →
IQ4_XS8.2 GB 10.8 GB
Too big Get file →
Q4_08.6 GB 11.3 GB
Too big Get file →
Q4_K_S8.6 GB 11.3 GB
Too big Get file →
Q4_K_M9.1 GB 11.8 GB
Too big Get file →
Q5_K_S10.4 GB 13.0 GB
Too big Get file →
Q5_K_M10.7 GB 13.3 GB
Too big Get file →
Q6_K12.3 GB 15.0 GB
Too big Get file →

For 8‑10 GB VRAM, use IQ2_S (est. 7.6 GB) or Q3_K_M (est. 10 GB). For 12‑15 GB VRAM, Q4_K_M (est. 11.8 GB) or Q5_K_S (est. 13 GB) are suitable. For 16 GB VRAM or more, Q6_K (est. 15 GB) provides the highest quality.

What GPU do you need for L3-Nymeria-15B?

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 IQ2_M (5.3 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (9.1 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (12.3 GB file, about 15.0 GB in use).

Which L3-Nymeria-15B quant should you choose?

Q4_K_M is the usual starting point for L3-Nymeria-15B: it balances file size and quality well. Here it is a 9.1 GB file.

If memory is tight, the smallest file is IQ1_S at 3.5 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
Parameters15B
Layers64
Trained context8,192 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyNymeria
Downloads (HF)1,072
Last updated2024-08-02

Frequently asked questions about L3-Nymeria-15B

How much VRAM does L3-Nymeria-15B need?

About 11.8 GB at Q4_K_M with an 8K context window. That is the 9.1 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-Nymeria-15B on an 8 GB GPU?

Yes, with IQ2_M: the 5.3 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of L3-Nymeria-15B GGUF?

It depends on the quant: IQ1_S is 3.5 GB, IQ1_M is 3.8 GB, IQ2_XXS is 4.3 GB, IQ2_XS is 4.7 GB, IQ2_S is 4.9 GB, IQ2_M is 5.3 GB and 15 more.

What context length does L3-Nymeria-15B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.1 GB at 8K and 2.1 GB at 8K.

Where can I download L3-Nymeria-15B GGUF?

The files are on Hugging Face in the mradermacher/L3-Nymeria-15B-i1-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-Nymeria-15B on 8 GB VRAM?

IQ2_S uses about 7.6 GB at 8k context, which fits within 8 GB VRAM. Other quants exceed this limit.

What context length does the model support?

The model was trained on 8192 context tokens and estimates are based on that length.

Is there a vision capability?

No vision support is provided with this model.

Other GGUFs of L3-Nymeria-15B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Nymeria models

All Nymeria →

Other medium models

All medium models →