OL

AMD OLMo 1B SFT DPO

OLMoGGUF by lmstudio-communityUpdated 2024-11-01
Download on Hugging Face
Parameters1.18B
Context2K
Layers16
Architectureolmo
Smallest quant0.7 GB
Quick answer

AMD OLMo 1B SFT DPO needs about 2.3 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.7 GB (Q3_K_L) to 1.3 GB (Q8_0).

AMD OLMo 1B SFT DPO – 1.18B parameter language model

AMD OLMo 1B SFT DPO is a 1.18B parameter model trained on AMD Instinct MI250 GPUs. It is supervised fine‑tuned on Tulu V2, OpenHermes‑2.5, WebInstructSub, and Code‑Feedback, then aligned with DPO on UltraFeedback. The model supports a 2048 token context length and is released under Apache‑2.0.

Good at

  • Instruction following
  • Chat‑style interactions
  • Multi‑turn dialogue

Limits

  • No vision support
  • Requires 2048 token context
  • Not suitable for safety‑critical use

Best for

  • Research prototypes
  • Small‑scale chatbots
  • Educational demos

Who it’s for. Researchers and developers who need a lightweight, open‑source LLM for experimentation. The model is ideal for those who can run it on local hardware and are comfortable with a 2048 token context limit.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L0.7 GB 1.4 GB
Fits Get file →
Q4_K_M0.7 GB 1.5 GB
Fits Get file →
Q6_K1.0 GB 1.7 GB
Fits Get file →
Q8_01.3 GB 2.0 GB
Fits Get file →

For 8 GB VRAM use Q4_K_M (0.73 GB file, ~2.3 GB VRAM). For 12 GB VRAM use Q6_K (0.97 GB file, ~2.5 GB VRAM). For 16 GB VRAM use Q8_0 (1.25 GB file, ~2.8 GB VRAM). Estimates are approximate.

What GPU do you need for AMD OLMo 1B SFT DPO?

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 Q8_0 (1.3 GB file, about 2.8 GB in use).

Which AMD OLMo 1B SFT DPO quant should you choose?

Q4_K_M is the usual starting point for AMD OLMo 1B SFT DPO: it balances file size and quality well. Here it is a 0.7 GB file.

The Q8_0 file is 1.3 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 Q3_K_L at 0.7 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

Architectureolmo
Parameters1.18B
Layers16
Trained context2,048 tokens
KV cache (fp16)128 KB per token

Source

Quantized bylmstudio-community
FamilyOLMo
Licenseapache-2.0
Downloads (HF)2,781
Last updated2024-11-01

Frequently asked questions about AMD OLMo 1B SFT DPO

How much VRAM does AMD OLMo 1B SFT DPO need?

About 2.3 GB at Q4_K_M with an 8K context window. That is the 0.7 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 OLMo 1B SFT DPO on an 8 GB GPU?

Yes, with Q8_0: the 1.3 GB file needs about 2.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of AMD OLMo 1B SFT DPO GGUF?

It depends on the quant: Q3_K_L is 0.7 GB, Q4_K_M is 0.7 GB, Q6_K is 1.0 GB, Q8_0 is 1.3 GB.

What context length does AMD OLMo 1B SFT DPO support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.3 GB at 2K.

Where can I download AMD OLMo 1B SFT DPO GGUF?

The files are on Hugging Face in the lmstudio-community/AMD-OLMo-1B-SFT-DPO-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 OLMo 1B SFT DPO 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 OLMo 1B SFT DPO on 8 GB VRAM?

Yes, the Q4_K_M quantization uses about 2.3 GB VRAM at 8 k context, which fits within an 8 GB budget.

Does the 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-OLMo-1B-SFT-DPO

Similar models

Browse all →

More from lmstudio-community

All by lmstudio-community →

More OLMo models

All OLMo →

Other tiny models

All tiny models →