HE

L3.1 HermesBreakGradientXL 12B i1

HermesbreakgradientxlGGUF by mradermacherUpdated 2024-09-09
Download on Hugging Face
Parameters12.2B
Context128K
Layers51
Architecturellama
Smallest quant2.9 GB
Quick answer

L3.1 HermesBreakGradientXL 12B i1 needs about 9.6 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.9 GB (IQ1_S) to 10.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.8 GB.

12B Llama model with 131072 token context, tool usage enabled

L3.1 HermesBreakGradientXL 12B i1 is a 12.2B parameter Llama model. It supports a 131072 token context and has tool usage capability. The model is available in multiple quantized formats.

Good at

  • Tool integration
  • Long context handling
  • Large parameter count

Limits

  • No vision support
  • License not specified
  • Large VRAM needed for higher quants

Best for

  • Complex tool‑driven tasks
  • Long‑form content generation
  • Research prototyping with large context

Who it’s for. Developers needing a 12B Llama model with extended context and tool support. Suitable for applications requiring detailed reasoning and multi‑step interactions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.9 GB 5.1 GB
Fits Get file →
IQ1_M3.1 GB 5.3 GB
Fits Get file →
IQ2_XXS3.5 GB 5.7 GB
Fits Get file →
IQ2_XS3.8 GB 6.0 GB
Fits Get file →
IQ2_S4.0 GB 6.3 GB
Fits Get file →
IQ2_M4.3 GB 6.6 GB
Fits Get file →
Q2_K4.7 GB 6.9 GB
Fits Get file →
IQ3_XXS4.9 GB 7.1 GB
Fits Get file →
IQ3_XS5.2 GB 7.4 GB
Tight Get file →
Q3_K_S5.4 GB 7.7 GB
Tight Get file →
IQ3_S5.5 GB 7.7 GB
Tight Get file →
IQ3_M5.6 GB 7.8 GB
Tight Get file →
Q3_K_M6.0 GB 8.2 GB
Too big Get file →
Q3_K_L6.5 GB 8.7 GB
Too big Get file →
IQ4_XS6.7 GB 8.9 GB
Too big Get file →
Q4_07.0 GB 9.2 GB
Too big Get file →
Q4_07.0 GB 9.2 GB
Too big Get file →
Q4_07.0 GB 9.2 GB
Too big Get file →
Q4_07.0 GB 9.2 GB
Too big Get file →
Q4_K_S7.0 GB 9.3 GB
Too big Get file →
Q4_K_M7.4 GB 9.6 GB
Too big Get file →
Q5_K_S8.4 GB 10.7 GB
Too big Get file →
Q5_K_M8.7 GB 10.9 GB
Too big Get file →
Q6_K10.0 GB 12.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (5.1 GB) or IQ1_M (5.3 GB). For 12 GB VRAM, Q6_K (10 GB) fits. For 16 GB VRAM, Q5_K_M (8.66 GB) or Q4_K_M (7.4 GB).

What GPU do you need for L3.1 HermesBreakGradientXL 12B i1?

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 IQ2_XS (3.8 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_M (5.6 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (8.7 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (10.0 GB file, about 12.2 GB in use).

Which L3.1 HermesBreakGradientXL 12B i1 quant should you choose?

Q4_K_M is the usual starting point for L3.1 HermesBreakGradientXL 12B i1: it balances file size and quality well. Here it is a 7.4 GB file.

If memory is tight, the smallest file is IQ1_S at 2.9 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
Parameters12.2B
Layers51
Trained context131,072 tokens
KV cache (fp16)204 KB per token

Source

Quantized bymradermacher
Downloads (HF)1,290
Last updated2024-09-09

Frequently asked questions about L3.1 HermesBreakGradientXL 12B i1

How much VRAM does L3.1 HermesBreakGradientXL 12B i1 need?

About 9.6 GB at Q4_K_M with an 8K context window. That is the 7.4 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 HermesBreakGradientXL 12B i1 on an 8 GB GPU?

Yes, with IQ3_M: the 5.6 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of L3.1 HermesBreakGradientXL 12B i1 GGUF?

It depends on the quant: IQ1_S is 2.9 GB, IQ1_M is 3.1 GB, IQ2_XXS is 3.5 GB, IQ2_XS is 3.8 GB, IQ2_S is 4.0 GB, IQ2_M is 4.3 GB and 18 more.

What context length does L3.1 HermesBreakGradientXL 12B i1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.8 GB at 32K.

Where can I download L3.1 HermesBreakGradientXL 12B i1 GGUF?

The files are on Hugging Face in the mradermacher/L3.1-HermesBreakGradientXL-12B-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 this model on 8 GB VRAM?

Yes, with IQ1_S or IQ1_M quant, which use about 5.1–5.3 GB at 8 k context.

Does it support vision?

No, the model has no vision capability.

What is the context length?

It supports 131072 tokens.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Hermesbreakgradientxl models

All Hermesbreakgradientxl →

Other medium models

All medium models →