MA

MadMix v0.2

MadmixGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

MadMix v0.2 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 14 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.

MadMix v0.2 – 7.24B llama model in GGUF format

MadMix v0.2 is a 7.24B parameter llama model quantized into GGUF files. It supports a 32768 token context window and is released under the apache-2.0 license. The model is available in multiple quantization levels for different memory budgets.

Good at

  • Large context handling
  • Flexible quantization options
  • Open source licensing

Limits

  • No vision support
  • No mixture of experts
  • Context limited to 32768 tokens

Best for

  • Chatbots requiring long context
  • Fine‑tuning on limited GPU memory
  • Research on llama architecture

Who it’s for. Developers and researchers who need a llama model with a large context window and flexible memory options. The model is suitable for those who prefer open‑source licensing and can work with GGUF files.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 4.3 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
IQ3_S3.2 GB 4.8 GB
Fits Get file →
IQ3_M3.3 GB 4.9 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 →
IQ4_XS3.9 GB 5.5 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_M (file size 4.37 GB, estimated memory 5.9 GB). For 12 GB VRAM, Q5_K_M (file size 5.13 GB, estimated memory 6.7 GB) offers a good balance. If more memory is available, Q6_K (file size 5.94 GB, estimated memory 7.5 GB) provides higher quality.

What GPU do you need for MadMix v0.2?

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 MadMix v0.2 quant should you choose?

Q4_K_M is the usual starting point for MadMix v0.2: 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 bymradermacher
FamilyMadmix
Licenseapache-2.0
Downloads (HF)945
Last updated2024-05-06

Frequently asked questions about MadMix v0.2

How much VRAM does MadMix v0.2 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 MadMix v0.2 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 MadMix v0.2 GGUF?

It depends on the quant: Q2_K is 2.7 GB, IQ3_XS is 3.0 GB, Q3_K_S is 3.2 GB, IQ3_S is 3.2 GB, IQ3_M is 3.3 GB, Q3_K_M is 3.5 GB and 8 more.

What context length does MadMix v0.2 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 MadMix v0.2 GGUF?

The files are on Hugging Face in the mradermacher/MadMix-v0.2-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 MadMix v0.2 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 MadMix v0.2 on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 5.9 GB of VRAM at 8 k context, which fits within an 8 GB budget.

Does MadMix v0.2 support vision tasks?

No, the model does not include vision capabilities.

What license applies to MadMix v0.2?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Madmix models

All Madmix →

Other small models

All small models →