SA

models--mergekit-community--mergekit-slerp-kxzcrwh

SaulGGUF by MaziyarPanahiUpdated 2024-06-18
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

models--mergekit-community--mergekit-slerp-kxzcrwh needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 2.7 GB (Q2_K) to 7.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

7.24B llama model fine‑tuned for legal instruction

This model is a 7.24B parameter llama architecture, derived from Equall/Saul-Base. It is optimized for legal domain instruction following. The model supports a 32768 token context window.

Good at

  • Legal instruction generation
  • Contextual legal reasoning
  • English language tasks

Limits

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

Best for

  • Legal document drafting
  • Contract analysis
  • Legal Q&A

Who it’s for. Users needing a local legal LLM for generating or analyzing legal text. Suitable for developers building legal chatbots or document assistants.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 4.3 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (4.14 GB file, ~5.7 GB memory). For 12 GB VRAM, Q5_K_S (5 GB file, ~6.6 GB memory) is a good balance. For 16 GB VRAM, Q6_K (5.94 GB file, ~7.5 GB memory) provides higher precision.

What GPU do you need for models--mergekit-community--mergekit-slerp-kxzcrwh?

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 Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).

Which models--mergekit-community--mergekit-slerp-kxzcrwh quant should you choose?

Q4_K_M is the usual starting point for models--mergekit-community--mergekit-slerp-kxzcrwh: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 GB, about 1.8 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 2.7 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byMaziyarPanahi
FamilySaul
Downloads (HF)587
Last updated2024-06-18

Frequently asked questions about models--mergekit-community--mergekit-slerp-kxzcrwh

How much VRAM does models--mergekit-community--mergekit-slerp-kxzcrwh need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 models--mergekit-community--mergekit-slerp-kxzcrwh on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of models--mergekit-community--mergekit-slerp-kxzcrwh GGUF?

It depends on the quant: Q2_K is 2.7 GB, Q3_K_S is 3.2 GB, Q3_K_M is 3.5 GB, Q3_K_L is 3.8 GB, Q4_K_S is 4.1 GB, Q4_K_M is 4.4 GB and 4 more.

What context length does models--mergekit-community--mergekit-slerp-kxzcrwh support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 models--mergekit-community--mergekit-slerp-kxzcrwh GGUF?

The files are on Hugging Face in the MaziyarPanahi/mergekit-slerp-kxzcrwh-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, using the Q4_K_S quantized file which requires about 5.7 GB of VRAM at 8 k context.

Does this model support vision tasks?

No, it is a text‑only model with no vision capability.

What is the maximum context length?

The model supports up to 32768 tokens of context.

Other GGUFs of Saul-Base

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Saul models

All Saul →

Other small models

All small models →