LL

AMD Llama 135m

LlamaGGUF by bartowskiUpdated 2024-09-28
Download on Hugging Face
Parameters134M
Context2K
Layers12
Architecturellama
Smallest quant0.1 GB
Quick answer

AMD Llama 135m needs about 0.9 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 18 quants, from 0.1 GB (IQ3_M) to 0.3 GB (F16).

AMD Llama 135m – a lightweight Llama model for code and text

AMD Llama 135m is a 0.134B parameter language model based on Llama2 architecture. It is trained on AMD Instinct MI250 accelerators and fine‑tuned on Python code from StarCoder. The model supports 2048 token context and is released under Apache‑2.0.

Good at

  • Code generation in Python
  • Lightweight inference on modest GPUs
  • Fast speculative decoding with CodeLlama

Limits

  • No vision support
  • Requires 2048 token context
  • License is Apache‑2.0

Best for

  • Embedded code assistants
  • Rapid prototyping of LLM applications
  • Low‑memory inference on edge devices

Who it’s for. Developers and researchers who need a small, open‑source Llama model for code tasks. The model is suitable for environments with limited GPU memory and for use in tools like LM Studio or llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M0.1 GB 0.6 GB
Fits Get file →
Q3_K_L0.1 GB 0.7 GB
Fits Get file →
IQ4_XS0.1 GB 0.7 GB
Fits Get file →
Q4_00.1 GB 0.7 GB
Fits Get file →
Q4_00.1 GB 0.7 GB
Fits Get file →
Q4_00.1 GB 0.7 GB
Fits Get file →
Q4_00.1 GB 0.7 GB
Fits Get file →
Q4_K_S0.1 GB 0.7 GB
Fits Get file →
Q4_K_M0.1 GB 0.7 GB
Fits Get file →
Q5_K_S0.1 GB 0.7 GB
Fits Get file →
Q5_K_M0.1 GB 0.7 GB
Fits Get file →
Q3_K_XL0.1 GB 0.7 GB
Fits Get file →
Q4_K_L0.1 GB 0.7 GB
Fits Get file →
Q6_K0.1 GB 0.7 GB
Fits Get file →
Q5_K_L0.1 GB 0.7 GB
Fits Get file →
Q6_K_L0.1 GB 0.7 GB
Fits Get file →
Q8_00.1 GB 0.7 GB
Fits Get file →
F160.3 GB 0.8 GB
Fits Get file →

For 8 GB VRAM, use IQ3_M (0.07 GB) or Q3_K_L (0.08 GB). If you have 4 GB VRAM, IQ4_XS (0.08 GB) is a good choice. For 2 GB VRAM, Q4_0 (0.08 GB) fits comfortably. Memory estimates are approximate.

What GPU do you need for AMD Llama 135m?

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 F16 (0.3 GB file, about 1.1 GB in use).

Which AMD Llama 135m quant should you choose?

Q4_K_M is the usual starting point for AMD Llama 135m: it balances file size and quality well. Here it is a 0.1 GB file.

The Q8_0 file is 0.1 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 IQ3_M at 0.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters134M
Layers12
Trained context2,048 tokens
KV cache (fp16)36 KB per token

Source

Quantized bybartowski
FamilyLlama
Licenseapache-2.0
Downloads (HF)768
Last updated2024-09-28

Frequently asked questions about AMD Llama 135m

How much VRAM does AMD Llama 135m need?

About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.1 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 AMD Llama 135m on an 8 GB GPU?

Yes, with F16: the 0.3 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of AMD Llama 135m GGUF?

It depends on the quant: IQ3_M is 0.1 GB, Q3_K_L is 0.1 GB, IQ4_XS is 0.1 GB, Q4_0 is 0.1 GB, Q4_0 is 0.1 GB, Q4_0 is 0.1 GB and 12 more.

What context length does AMD Llama 135m support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.1 GB at 2K.

Where can I download AMD Llama 135m GGUF?

The files are on Hugging Face in the bartowski/AMD-Llama-135m-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 AMD Llama 135m 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 AMD Llama 135m on 8 GB VRAM?

Yes, the IQ3_M and Q3_K_L quantizations are 0.07–0.08 GB and fit easily on 8 GB VRAM.

Does this model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of AMD-Llama-135m

Similar models

Browse all →

More from bartowski

All by bartowski →

More Llama models

All Llama →

Other tiny models

All tiny models →