EX

Extended-Mega-Mash-262K-8B-L3

ExtendedGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters8B
Context256K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

Extended-Mega-Mash-262K-8B-L3 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 21 quants, from 2.0 GB (IQ1_S) to 6.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

8B Llama model with 262K context and multiple IQ/quant options

Extended-Mega-Mash-262K-8B-L3 is a 8B parameter Llama model merged from several sources. It supports 262,144 token context and is available in a variety of quantizations. The model is licensed under cc‑by‑nc‑4.0.

Good at

  • Large context handling
  • Multiple quantization choices
  • Open source availability

Limits

  • No vision support
  • License restricts commercial use
  • Requires 8K context for memory estimates

Best for

  • Chatbots needing long context
  • Research prototyping with low VRAM
  • Fine‑tuning on custom data

Who it’s for. Developers and researchers who need a large‑context Llama model and are comfortable with open‑source licensing. The model is suitable for non‑commercial projects and experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ1_M2.2 GB 3.7 GB
Fits Get file →
IQ2_XXS2.4 GB 4.0 GB
Fits Get file →
IQ2_XS2.6 GB 4.2 GB
Fits Get file →
IQ2_S2.8 GB 4.3 GB
Fits Get file →
IQ2_M2.9 GB 4.5 GB
Fits Get file →
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XXS3.3 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.4 GB 6.0 GB
Fits Get file →
Q4_04.7 GB 6.2 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (file size 2.02 GB, estimated 3.6 GB memory). If more VRAM is available, IQ4_K_M (4.92 GB, 6.5 GB memory) or Q5_K_M (5.73 GB, 7.3 GB memory) provide better quality. Larger VRAM allows Q6_K (6.6 GB, 8.2 GB memory).

What GPU do you need for Extended-Mega-Mash-262K-8B-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: the best quant that fits is IQ2_XXS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).

Which Extended-Mega-Mash-262K-8B-L3 quant should you choose?

Q4_K_M is the usual starting point for Extended-Mega-Mash-262K-8B-L3: it balances file size and quality well. Here it is a 4.9 GB file.

If memory is tight, the smallest file is IQ1_S at 2.0 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
Parameters8B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyExtended
Downloads (HF)1,764
Last updated2024-08-02

Frequently asked questions about Extended-Mega-Mash-262K-8B-L3

How much VRAM does Extended-Mega-Mash-262K-8B-L3 need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Extended-Mega-Mash-262K-8B-L3 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Extended-Mega-Mash-262K-8B-L3 GGUF?

It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB, IQ2_M is 2.9 GB and 15 more.

What context length does Extended-Mega-Mash-262K-8B-L3 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Extended-Mega-Mash-262K-8B-L3 GGUF?

The files are on Hugging Face in the mradermacher/Extended-Mega-Mash-262K-8B-L3-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 Extended-Mega-Mash-262K-8B-L3 use?

Hugging Face lists the license as cc-by-nc-4.0. 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 this model on 8 GB VRAM?

Yes, the IQ1_S quant uses about 3.6 GB memory at 8K context, fitting within 8 GB VRAM.

Is the model suitable for commercial use?

No, the cc‑by‑nc‑4.0 license prohibits commercial use without permission.

Does the model support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of Extended-Mega-Mash-262K-8B-L3

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Extended models

All Extended →

Other small models

All small models →