SM

SmolLlamix 8x101M

SmolllamixGGUF by afridevaUpdated 2023-12-16
Download on Hugging Face
Parameters399M
Context32K
Layers6
Architecturellama
Smallest quant0.1 GB
Quick answer

SmolLlamix 8x101M needs about 0.8 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.1 GB (Q2_K) to 0.8 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 0.2 GB.

SmolLlamix 8x101M – a 0.399B parameter Mixtral model

SmolLlamix 8x101M is a 0.399B parameter llama architecture model. It is a mixture of experts trained on a small subset of RedPajama. The model supports a 32768 token context length.

Good at

  • Large context handling
  • Efficient inference with low‑memory quants
  • Mixtral architecture

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is apache‑2.0

Best for

  • Chatting with long context
  • Fine‑tuning on small datasets
  • Running on GPUs with limited VRAM

Who it’s for. Developers and researchers who need a small, efficient Mixtral model with long context. The model is suitable for experimentation and lightweight deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 0.7 GB
Fits Get file →
Q3_K_M0.2 GB 0.7 GB
Fits Get file →
Q4_K_M0.2 GB 0.8 GB
Fits Get file →
Q5_K_M0.3 GB 0.8 GB
Fits Get file →
Q6_K0.3 GB 0.9 GB
Fits Get file →
Q8_00.4 GB 1.0 GB
Fits Get file →
—0.8 GB 1.3 GB
Fits Get file →

For 8 GB VRAM use Q4_K_M (0.23 GB file, 0.8 GB memory at 8k context). For 6 GB VRAM use Q3_K_M (0.18 GB file, 0.7 GB memory). For 4 GB VRAM use Q2_K (0.15 GB file, 0.7 GB memory).

What GPU do you need for SmolLlamix 8x101M?

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 the main file (0.8 GB file, about 1.3 GB in use).

Which SmolLlamix 8x101M quant should you choose?

Q4_K_M is the usual starting point for SmolLlamix 8x101M: it balances file size and quality well. Here it is a 0.2 GB file.

The Q8_0 file is 0.4 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 0.1 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
Parameters399M (approximate, mixture of experts)
Layers6
Trained context32,768 tokens
KV cache (fp16)6 KB per token

Source

Quantized byafrideva
Licenseapache-2.0
Downloads (HF)637
Last updated2023-12-16

Frequently asked questions about SmolLlamix 8x101M

How much VRAM does SmolLlamix 8x101M need?

About 0.8 GB at Q4_K_M with an 8K context window. That is the 0.2 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 SmolLlamix 8x101M on an 8 GB GPU?

Yes, with the smaller files: the 0.8 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SmolLlamix 8x101M GGUF?

It depends on the quant: Q2_K is 0.1 GB, Q3_K_M is 0.2 GB, Q4_K_M is 0.2 GB, Q5_K_M is 0.3 GB, Q6_K is 0.3 GB, Q8_0 is 0.4 GB and 1 more.

What context length does SmolLlamix 8x101M support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.2 GB at 32K.

Where can I download SmolLlamix 8x101M GGUF?

The files are on Hugging Face in the afrideva/SmolLlamix-8x101M-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 SmolLlamix 8x101M 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 SmolLlamix 8x101M on 8 GB VRAM?

Yes, using Q4_K_M or Q3_K_M quantizations keeps VRAM usage below 8 GB.

Does the model support image input?

No, the model has no vision capabilities.

What is the context length of this model?

The model supports a 32768 token context length.

Other GGUFs of SmolLlamix-8x101M

Similar models

Browse all →

More from afrideva

All by afrideva →

More Smolllamix models

All Smolllamix →

Other tiny models

All tiny models →