MA

MAmmoTH2-8x7B-Plus

MammothGGUF by mradermacherUpdated 2024-05-24
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant17.3 GB
Quick answer

MAmmoTH2-8x7B-Plus needs about 30.0 GB of memory at Q4_K_M (a 28.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 14 quants, from 17.3 GB (Q2_K) to 49.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

MAmmoTH2-8x7B-Plus: 46.7B parameter Llama-based model with 32k context

MAmmoTH2-8x7B-Plus is a 46.7B parameter Llama model fine‑tuned on 10M instruction‑response pairs. It supports a 32768 token context window and is released under the MIT license. The model is part of the MAmmoTH2 family and is a mixture of experts.

Good at

  • Advanced reasoning tasks
  • Instruction following
  • Math problem solving

Limits

  • No vision support
  • Large VRAM requirement for higher quants
  • Requires 8k context for memory estimates

Best for

  • Math tutoring
  • Complex instruction generation
  • Chatbot reasoning

Who it’s for. Developers and researchers needing a large, instruction‑tuned Llama model for reasoning tasks. The model is suitable for applications that can accommodate its memory footprint and do not require vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K17.3 GB 18.9 GB
Too big Get file →
IQ3_XS19.4 GB 20.9 GB
Too big Get file →
IQ3_S20.4 GB 22.0 GB
Too big Get file →
Q3_K_S20.4 GB 22.0 GB
Too big Get file →
IQ3_M21.4 GB 23.0 GB
Too big Get file →
Q3_K_M22.5 GB 24.1 GB
Too big Get file →
Q3_K_L24.2 GB 25.7 GB
Too big Get file →
IQ4_XS25.4 GB 26.9 GB
Too big Get file →
Q4_K_S26.7 GB 28.3 GB
Too big Get file →
Q4_K_M28.4 GB 30.0 GB
Too big Get file →
Q5_K_S32.2 GB 33.8 GB
Too big Get file →
Q5_K_M33.2 GB 34.8 GB
Too big Get file →
Q6_K38.4 GB 40.0 GB
Too big Get file →
Q8_049.6 GB 51.2 GB
Too big Get file →

For 8 GB VRAM use Q2_K (17.31 GB file, 18.9 GB memory at 8k context). For 12 GB VRAM use Q3_K_M (22.55 GB file, 24.1 GB memory). For 16 GB VRAM use Q4_K_M (28.45 GB file, 30 GB memory). Estimates are approximate.

What GPU do you need for MAmmoTH2-8x7B-Plus?

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 IQ3_M (21.4 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (28.4 GB file, about 30.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (38.4 GB file, about 40.0 GB in use).

Which MAmmoTH2-8x7B-Plus quant should you choose?

Q4_K_M is the usual starting point for MAmmoTH2-8x7B-Plus: it balances file size and quality well. Here it is a 28.4 GB file.

The Q8_0 file is 49.6 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 17.3 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
Parameters46.7B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyMammoth
Licensemit
Downloads (HF)1,128
Last updated2024-05-24

Frequently asked questions about MAmmoTH2-8x7B-Plus

How much VRAM does MAmmoTH2-8x7B-Plus need?

About 30.0 GB at Q4_K_M with an 8K context window. That is the 28.4 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 MAmmoTH2-8x7B-Plus 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 MAmmoTH2-8x7B-Plus GGUF?

It depends on the quant: Q2_K is 17.3 GB, IQ3_XS is 19.4 GB, IQ3_S is 20.4 GB, Q3_K_S is 20.4 GB, IQ3_M is 21.4 GB, Q3_K_M is 22.5 GB and 8 more.

What context length does MAmmoTH2-8x7B-Plus 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 MAmmoTH2-8x7B-Plus GGUF?

The files are on Hugging Face in the mradermacher/MAmmoTH2-8x7B-Plus-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 MAmmoTH2-8x7B-Plus use?

Hugging Face lists the license as mit. 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 MAmmoTH2-8x7B-Plus on 8 GB VRAM?

Use the Q2_K quant, which requires about 18.9 GB memory at 8k context, so 8 GB VRAM is insufficient.

Is the model licensed for commercial use?

The model is released under the MIT license, which allows commercial use.

Does the model support vision inputs?

No, the model does not support vision capabilities.

Other GGUFs of MAmmoTH2-8x7B-Plus

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mammoth models

All Mammoth →

Other large models

All large models →