MA

MAmmoTH2-8B-Plus

MammothGGUF by mradermacherUpdated 2024-06-28
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant3.2 GB
Quick answer

MAmmoTH2-8B-Plus 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 15 quants, from 3.2 GB (Q2_K) to 16.1 GB (F16).

MAmmoTH2-8B-Plus: 8.03B parameter Llama model tuned for reasoning

MAmmoTH2-8B-Plus is a llama architecture model with 8.03B parameters. It is fine‑tuned on a large instruction dataset to improve reasoning on math and general tasks. The model supports a 8192 token context window and is released under the MIT license.

Good at

  • Reasoning on math problems
  • Instruction following
  • General chatbot tasks

Limits

  • No vision support
  • Requires 8192 token context
  • MIT license limits commercial use

Best for

  • Math tutoring
  • Chatbot development
  • Educational content generation

Who it’s for. Developers building reasoning‑heavy chatbots or educational tools. Researchers needing a large Llama‑based model for math benchmarks. Users with GPU memory to run 8B models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.2 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_XS4.5 GB 6.1 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 →
Q8_08.5 GB 10.1 GB
Too big Get file →
F1616.1 GB 17.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 4.92 GB, estimated 6.5 GB memory). For 12 GB VRAM, Q5_K_M (5.73 GB, 7.3 GB memory) or Q6_K (6.6 GB, 8.2 GB memory). For 24 GB VRAM, Q8_0 (8.54 GB, 10.1 GB memory) or F16 (16.07 GB, 17.6 GB memory).

What GPU do you need for MAmmoTH2-8B-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: the best quant that fits is Q3_K_L (4.3 GB file, about 5.9 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 Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).

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

Q4_K_M is the usual starting point for MAmmoTH2-8B-Plus: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 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 3.2 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
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyMammoth
Licensemit
Downloads (HF)765
Last updated2024-06-28

Frequently asked questions about MAmmoTH2-8B-Plus

How much VRAM does MAmmoTH2-8B-Plus 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 MAmmoTH2-8B-Plus 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 MAmmoTH2-8B-Plus GGUF?

It depends on the quant: Q2_K is 3.2 GB, IQ3_XS is 3.5 GB, Q3_K_S is 3.7 GB, IQ3_S is 3.7 GB, IQ3_M is 3.8 GB, Q3_K_M is 4.0 GB and 9 more.

What context length does MAmmoTH2-8B-Plus support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download MAmmoTH2-8B-Plus GGUF?

The files are on Hugging Face in the mradermacher/MAmmoTH2-8B-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 MAmmoTH2-8B-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 MAmmoTH2-8B-Plus on 8 GB VRAM?

Use the Q4_K_M quant, which requires about 6.5 GB memory at 8k context. It fits within 8 GB VRAM with some overhead.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the MIT license, allowing free use with attribution.

Other GGUFs of MAmmoTH2-8B-Plus

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mammoth models

All Mammoth →

Other small models

All small models →