HA

HaloMaidRP-v1.33-15B-L3

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

HaloMaidRP-v1.33-15B-L3 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 Llama‑3 based model with multiple IQ and Q quantizations

HaloMaidRP‑v1.33‑15B‑L3 is a 15‑billion‑parameter Llama‑3 model merged from several 8B sources. It supports a 8192‑token context window and offers a range of GGUF quantizations for different memory budgets. The model is provided without a license and contains no vision capabilities.

Good at

  • Large context handling
  • Flexible quantization options
  • Stable 15B performance

Limits

  • No license specified
  • No vision support
  • Requires 8K context for full capability

Best for

  • Chatting with long documents
  • Fine‑tuning smaller models
  • Running on GPUs with 8‑16 GB VRAM

Who it’s for. Developers and researchers who need a 15B Llama‑3 model with a large context window and multiple quantization choices. The model is suitable for those who can manage the lack of a license and the absence of vision features.

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 GB VRAM use IQ1_S (3.5 GB, 6.1 GB memory). For 12 GB VRAM use Q4_K_M (9.11 GB, 11.8 GB memory). For 16 GB VRAM use Q5_K_M (10.67 GB, 13.3 GB memory). Estimates are approximate.

What GPU do you need for HaloMaidRP-v1.33-15B-L3?

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 HaloMaidRP-v1.33-15B-L3 quant should you choose?

Q4_K_M is the usual starting point for HaloMaidRP-v1.33-15B-L3: 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
Downloads (HF)518
Last updated2024-08-02

Frequently asked questions about HaloMaidRP-v1.33-15B-L3

How much VRAM does HaloMaidRP-v1.33-15B-L3 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 HaloMaidRP-v1.33-15B-L3 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 HaloMaidRP-v1.33-15B-L3 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 HaloMaidRP-v1.33-15B-L3 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 HaloMaidRP-v1.33-15B-L3 GGUF?

The files are on Hugging Face in the mradermacher/HaloMaidRP-v1.33-15B-L3-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 HaloMaidRP on 8 GB VRAM?

Yes, use the IQ1_S or IQ1_M quantization; they require about 6.1–6.4 GB of VRAM at 8K context.

Does the model support image input?

No, the model has no vision capabilities.

Is there a license for this model?

No license is specified; use at your own risk.

Other GGUFs of HaloMaidRP-v1.33-15B-L3

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Halomaidrp models

All Halomaidrp →

Other medium models

All medium models →