OL

OLMo 7B Twin 2T Hf

OLMoGGUF by RichardErkhovUpdated 2024-09-18
Download on Hugging Face
Parameters6.89B
Context2K
Layers32
Architectureolmo
Smallest quant2.6 GB
Quick answer

OLMo 7B Twin 2T Hf needs about 9.0 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 22 quants, from 2.6 GB (Q2_K) to 7.3 GB (Q8_0).

OLMo 7B Twin 2T Hf – 6.89B parameter autoregressive model

OLMo 7B Twin 2T Hf is a 6.89B parameter transformer model trained on the Dolma dataset. It supports 2048 token context and is released under Apache‑2.0. The model is available in multiple GGUF quantizations.

Good at

  • English language generation
  • Autoregressive text completion
  • Fine‑tuning for downstream tasks

Limits

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

Best for

  • Chatbot prototypes
  • Text summarization
  • Custom fine‑tuning

Who it’s for. Developers and researchers needing a medium‑size language model for text‑only applications. The model is suitable for local inference with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.6 GB 4.2 GB
Fits Get file →
IQ3_XS2.9 GB 4.5 GB
Fits Get file →
IQ3_S3.0 GB 4.6 GB
Fits Get file →
Q3_K_S3.0 GB 4.6 GB
Fits Get file →
IQ3_M3.2 GB 4.8 GB
Fits Get file →
Q3_K3.4 GB 5.0 GB
Fits Get file →
Q3_K_M3.4 GB 5.0 GB
Fits Get file →
Q3_K_L3.7 GB 5.3 GB
Fits Get file →
IQ4_XS3.7 GB 5.3 GB
Fits Get file →
Q4_03.9 GB 5.5 GB
Fits Get file →
IQ4_NL4.0 GB 5.5 GB
Fits Get file →
Q4_K_S4.0 GB 5.5 GB
Fits Get file →
Q4_K4.2 GB 5.8 GB
Fits Get file →
Q4_K_M4.2 GB 5.8 GB
Fits Get file →
Q4_14.3 GB 5.9 GB
Fits Get file →
Q5_04.8 GB 6.3 GB
Fits Get file →
Q5_K_S4.8 GB 6.3 GB
Fits Get file →
Q5_K4.9 GB 6.5 GB
Fits Get file →
Q5_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_15.2 GB 6.8 GB
Fits Get file →
Q6_K5.7 GB 7.2 GB
Tight Get file →
Q8_07.3 GB 8.9 GB
Too big Get file →

For 8 GB VRAM use Q4_0 (3.93 GB file, ~8.7 GB memory). For 12 GB VRAM use Q6_K (5.65 GB file, ~10.4 GB memory). For 16 GB VRAM use Q8_0 (7.32 GB file, ~12.1 GB memory). Estimates are approximate.

What GPU do you need for OLMo 7B Twin 2T Hf?

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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is IQ3_M (3.2 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 10.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.3 GB file, about 12.1 GB in use).

Which OLMo 7B Twin 2T Hf quant should you choose?

Q4_K_M is the usual starting point for OLMo 7B Twin 2T Hf: it balances file size and quality well. Here it is a 4.2 GB file.

The Q8_0 file is 7.3 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 Q2_K at 2.6 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

Architectureolmo
Parameters6.89B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized byRichardErkhov
FamilyOLMo
Licenseapache-2.0
Downloads (HF)713
Last updated2024-09-18

Frequently asked questions about OLMo 7B Twin 2T Hf

How much VRAM does OLMo 7B Twin 2T Hf need?

About 9.0 GB at Q4_K_M with an 8K context window. That is the 4.2 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 OLMo 7B Twin 2T Hf on an 8 GB GPU?

Yes, with IQ3_M: the 3.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of OLMo 7B Twin 2T Hf GGUF?

It depends on the quant: Q2_K is 2.6 GB, IQ3_XS is 2.9 GB, IQ3_S is 3.0 GB, Q3_K_S is 3.0 GB, IQ3_M is 3.2 GB, Q3_K is 3.4 GB and 16 more.

What context length does OLMo 7B Twin 2T Hf support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download OLMo 7B Twin 2T Hf GGUF?

The files are on Hugging Face in the RichardErkhov/allenai_-_OLMo-7B-Twin-2T-hf-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 OLMo 7B Twin 2T Hf 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 OLMo 7B Twin 2T Hf on 8 GB VRAM?

Yes, use the Q4_0 quantization which requires about 8.7 GB of VRAM at 8k context.

Does this model support image inputs?

No, the model is text‑only and has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More OLMo models

All OLMo →

Other small models

All small models →