AL

alfred 40B 1023

AlfredGGUF by TheBlokeUpdated 2023-11-17
Download on Hugging Face
Parameters41.8B
Context2K
Layers60
Architecturefalcon
Smallest quant17.4 GB
Quick answer

alfred 40B 1023 needs about 27.0 GB of memory at Q4_K_M (a 25.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 12 quants, from 17.4 GB (Q2_K) to 44.5 GB (Q8_0).

Alfred 40B 1023 – a Falcon‑based large language model with extended context

Alfred 40B 1023 is a 41.8 billion parameter Falcon finetune released in October 2023. It supports 8192‑token context and is available under the Apache 2.0 license. The model is trained primarily on English, German, Spanish, French and limited other European languages.

Good at

  • Long‑context reasoning
  • Multilingual text generation
  • Chat and instruction tasks

Limits

  • No vision support
  • Limited to listed languages
  • Requires large VRAM for full precision

Best for

  • Chatbot development
  • Research on long‑context models
  • Instruction‑based applications

Who it’s for. Developers and researchers who need a large, open‑source language model with extended context. The model is suitable for local inference on systems with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K17.4 GB 18.2 GB
Too big Get file →
Q3_K_S18.3 GB 19.1 GB
Too big Get file →
Q3_K_M20.1 GB 20.8 GB
Too big Get file →
Q3_K_L21.6 GB 22.4 GB
Too big Get file →
Q4_023.8 GB 24.6 GB
Too big Get file →
Q4_K_S23.8 GB 24.6 GB
Too big Get file →
Q4_K_M25.5 GB 26.2 GB
Too big Get file →
Q5_029.0 GB 29.7 GB
Too big Get file →
Q5_K_S29.0 GB 29.7 GB
Too big Get file →
Q5_K_M30.6 GB 31.4 GB
Too big Get file →
Q6_K34.5 GB 35.2 GB
Too big Get file →
Q8_044.5 GB 45.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (25.45 GB file, ~27 GB RAM). For 12 GB VRAM, Q5_K_M (30.64 GB file, ~32.1 GB RAM). For 16 GB VRAM, Q6_K (34.46 GB file, ~36 GB RAM). Estimates are approximate.

What GPU do you need for alfred 40B 1023?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q3_K_L (21.6 GB file, about 23.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_0 (29.0 GB file, about 30.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (44.5 GB file, about 46.0 GB in use).

Which alfred 40B 1023 quant should you choose?

Q4_K_M is the usual starting point for alfred 40B 1023: it balances file size and quality well. Here it is a 25.5 GB file.

The Q8_0 file is 44.5 GB, about 1.7 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 17.4 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

Architecturefalcon
Parameters41.8B
Layers60
Trained context2,048 tokens
KV cache (fp16)120 KB per token

Source

Quantized byTheBloke
FamilyAlfred
Licenseapache-2.0
Downloads (HF)1,664
Last updated2023-11-17

Frequently asked questions about alfred 40B 1023

How much VRAM does alfred 40B 1023 need?

About 27.0 GB at Q4_K_M with an 8K context window. That is the 25.5 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 alfred 40B 1023 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of alfred 40B 1023 GGUF?

It depends on the quant: Q2_K is 17.4 GB, Q3_K_S is 18.3 GB, Q3_K_M is 20.1 GB, Q3_K_L is 21.6 GB, Q4_0 is 23.8 GB, Q4_K_S is 23.8 GB and 6 more.

What context length does alfred 40B 1023 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.0 GB at 8K and 0.3 GB at 2K.

Where can I download alfred 40B 1023 GGUF?

The files are on Hugging Face in the TheBloke/alfred-40B-1023-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 alfred 40B 1023 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 Alfred 40B 1023 on 8 GB VRAM?

Use the Q4_K_M quantised model; it requires about 27 GB of RAM and a 25.45 GB file size.

Does the model support image input?

No, Alfred 40B 1023 is a text‑only model with no vision capabilities.

What license does the model use?

The model is released under the Apache 2.0 license.

Other GGUFs of alfred-40b-1023

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Alfred models

All Alfred →

Other large models

All large models →