notHumpback-Myx needs about 3.5 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 1.4 GB (Q2_K) to 3.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
notHumpback-Myx: 3.21B llama model fine‑tuned on instruction backtranslation
notHumpback-Myx is a 3.21B parameter llama model trained on a self‑augmented web corpus. It uses instruction backtranslation to generate high‑quality instruction pairs. The model is released under apache‑2.0.
Good at
- Instruction generation from web text
- Self‑curated dataset creation
- Fine‑tuned on oasst1
Limits
- No vision support
- Large context requires high VRAM
- License is apache‑2.0
Best for
- Generating instruction datasets
- Fine‑tuning instruction models
- Research on self‑augmentation
Who it’s for. Researchers and developers needing a backward model for instruction generation. The model is suitable for those who can handle the memory demands of a 3.21B parameter llama.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.4 GB | 2.8 GB | Fits | Get file → | |
| IQ3_XS | 1.5 GB | 2.9 GB | Fits | Get file → | |
| IQ3_S | 1.5 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 3.0 GB | Fits | Get file → | |
| IQ3_M | 1.6 GB | 3.0 GB | Fits | Get file → | |
| Q3_K | 1.7 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_M | 1.7 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_L | 1.8 GB | 3.3 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 3.3 GB | Fits | Get file → | |
| Q4_0 | 1.9 GB | 3.4 GB | Fits | Get file → | |
| IQ4_NL | 1.9 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_S | 1.9 GB | 3.4 GB | Fits | Get file → | |
| Q4_K | 2.0 GB | 3.5 GB | Fits | Get file → | |
| Q4_K_M | 2.0 GB | 3.5 GB | Fits | Get file → | |
| Q4_1 | 2.1 GB | 3.5 GB | Fits | Get file → | |
| Q5_0 | 2.3 GB | 3.7 GB | Fits | Get file → | |
| Q5_K_S | 2.3 GB | 3.7 GB | Fits | Get file → | |
| Q5_K | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_M | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q5_1 | 2.4 GB | 3.9 GB | Fits | Get file → | |
| Q6_K | 2.6 GB | 4.1 GB | Fits | Get file → | |
| Q8_0 | 3.4 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM use Q4_K or Q4_K_M (file size 2.02 GB, memory 3.5 GB). For 12 GB VRAM use Q5_K or Q5_K_M (file size 2.32 GB, memory 3.8 GB). For 16 GB VRAM use Q6_K (file size 2.64 GB, memory 4.1 GB).
What GPU do you need for notHumpback-Myx?
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 Q5_1 (2.4 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.9 GB in use).
Which notHumpback-Myx quant should you choose?
Q4_K_M is the usual starting point for notHumpback-Myx: it balances file size and quality well. Here it is a 2.0 GB file.
The Q8_0 file is 3.4 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 1.4 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
Source
Frequently asked questions about notHumpback-Myx
How much VRAM does notHumpback-Myx need?
About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.0 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 notHumpback-Myx on an 8 GB GPU?
Yes, with Q8_0: the 3.4 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of notHumpback-Myx GGUF?
It depends on the quant: Q2_K is 1.4 GB, IQ3_XS is 1.5 GB, IQ3_S is 1.5 GB, Q3_K_S is 1.5 GB, IQ3_M is 1.6 GB, Q3_K is 1.7 GB and 16 more.
What context length does notHumpback-Myx support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download notHumpback-Myx GGUF?
The files are on Hugging Face in the RichardErkhov/Alepach_-_notHumpback-Myx-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 notHumpback-Myx 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 notHumpback-Myx on 8 GB VRAM?
Yes, using Q4_K or Q4_K_M quantization, which requires about 3.5 GB of VRAM at 8 k context.
Does notHumpback-Myx support vision tasks?
No, the model has no vision capabilities.