LL

Jallabi 40B

LlamaGGUF by mradermacherUpdated 2024-09-17
Download on Hugging Face
Parameters18.8B
Context4K
Layers32
Architecturellama
Smallest quant4.2 GB
Quick answer

Jallabi 40B needs about 12.9 GB of memory at Q4_K_M (a 11.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 21 quants, from 4.2 GB (IQ1_S) to 15.4 GB (Q6_K).

Jallabi 40B – 18.8B parameter Llama model in GGUF format

Jallabi 40B is an 18.8B parameter Llama model quantized into GGUF files. It supports a 4096 token context window and is released under the apache-2.0 license. The model is available in multiple quantization levels from IQ1_S to Q6_K.

Good at

  • Large context reasoning
  • High‑parameter language modeling
  • Fine‑grained text generation

Limits

  • No vision support
  • Requires at least 5.8 GB VRAM for IQ1_S at 8 k context
  • License is apache‑2.0

Best for

  • Chatbot back‑end
  • Research prototyping
  • Content drafting

Who it’s for. Developers and researchers needing a large Llama model in GGUF format. The model is suitable for local deployment on machines with sufficient VRAM and for use with llama.cpp or similar runtimes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.2 GB 5.3 GB
Fits Get file →
IQ1_M4.6 GB 5.6 GB
Fits Get file →
IQ2_XXS5.2 GB 6.2 GB
Fits Get file →
IQ2_XS5.7 GB 6.8 GB
Fits Get file →
IQ2_S6.1 GB 7.1 GB
Fits Get file →
IQ2_M6.5 GB 7.6 GB
Tight Get file →
Q2_K7.1 GB 8.1 GB
Too big Get file →
IQ3_XXS7.4 GB 8.4 GB
Too big Get file →
IQ3_XS7.9 GB 8.9 GB
Too big Get file →
Q3_K_S8.2 GB 9.3 GB
Too big Get file →
IQ3_S8.3 GB 9.3 GB
Too big Get file →
IQ3_M8.6 GB 9.6 GB
Too big Get file →
Q3_K_M9.2 GB 10.2 GB
Too big Get file →
Q3_K_L9.9 GB 11.0 GB
Too big Get file →
IQ4_XS10.1 GB 11.2 GB
Too big Get file →
Q4_010.7 GB 11.8 GB
Too big Get file →
Q4_K_S10.8 GB 11.8 GB
Too big Get file →
Q4_K_M11.3 GB 12.4 GB
Too big Get file →
Q5_K_S13.0 GB 14.0 GB
Too big Get file →
Q5_K_M13.3 GB 14.3 GB
Too big Get file →
Q6_K15.4 GB 16.4 GB
Too big Get file →

For 8 GB VRAM, IQ1_S (4.22 GB, 5.8 GB memory) or IQ1_M (4.58 GB, 6.2 GB memory) are suitable. If 12 GB VRAM is available, Q4_K_M (11.31 GB, 12.9 GB memory) offers higher quality. For the best trade‑off between size and quality, Q3_K_M (9.16 GB, 10.7 GB memory) is recommended.

What GPU do you need for Jallabi 40B?

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 IQ1_S (4.2 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ2_S (6.1 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ4_XS (10.1 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (13.3 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (15.4 GB file, about 17.0 GB in use).

Which Jallabi 40B quant should you choose?

Q4_K_M is the usual starting point for Jallabi 40B: it balances file size and quality well. Here it is a 11.3 GB file.

If memory is tight, the smallest file is IQ1_S at 4.2 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
Parameters18.8B
Layers32
Trained context4,096 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licenseapache-2.0
Downloads (HF)740
Last updated2024-09-17

Frequently asked questions about Jallabi 40B

How much VRAM does Jallabi 40B need?

About 12.9 GB at Q4_K_M with an 8K context window. That is the 11.3 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 Jallabi 40B on an 8 GB GPU?

Yes, with IQ2_S: the 6.1 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Jallabi 40B GGUF?

It depends on the quant: IQ1_S is 4.2 GB, IQ1_M is 4.6 GB, IQ2_XXS is 5.2 GB, IQ2_XS is 5.7 GB, IQ2_S is 6.1 GB, IQ2_M is 6.5 GB and 15 more.

What context length does Jallabi 40B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.

Where can I download Jallabi 40B GGUF?

The files are on Hugging Face in the mradermacher/llama3-Jallabi-40B-s-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Jallabi 40B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Jallabi 40B on 8 GB VRAM?

Yes, the IQ1_S quant requires 5.8 GB VRAM at 8 k context, which fits within 8 GB. IQ1_M needs 6.2 GB.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other medium models

All medium models →