CE

Cerebras OPT Fusion i1

CerebrasGGUF by mradermacherUpdated 2025-03-05
Download on Hugging Face
Parameters6.86B
Context2K
Layers32
Architecturegpt2
Smallest quant1.6 GB
Quick answer

Cerebras OPT Fusion i1 needs about 9.2 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 1.6 GB (IQ1_S) to 5.7 GB (Q6_K).

Cerebras OPT Fusion i1 – 6.86B parameter hybrid GPT‑2 model

Cerebras OPT Fusion i1 is a 6.86B parameter hybrid language model built by merging Cerebras‑GPT‑6.7B and OPT‑6.7B with Linear Merge. It is released under the MIT license and supports a 2048 token context window.

Good at

  • Text generation
  • Conversational AI
  • Creative writing

Limits

  • No vision support
  • May produce inaccurate or biased content
  • Performance varies across tasks

Best for

  • Research on hybrid model merging
  • Experimenting with GPT‑2 style models
  • Benchmarking quantization effects

Who it’s for. Researchers and developers interested in hybrid language models and quantization techniques. The model is suitable for experimentation and academic studies rather than production deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 3.2 GB
Fits Get file →
IQ1_M1.7 GB 3.3 GB
Fits Get file →
IQ2_XXS1.9 GB 3.5 GB
Fits Get file →
IQ2_XS2.1 GB 3.7 GB
Fits Get file →
IQ2_S2.2 GB 3.8 GB
Fits Get file →
IQ2_M2.4 GB 4.0 GB
Fits Get file →
Q2_K_S2.5 GB 4.0 GB
Fits Get file →
Q2_K2.7 GB 4.2 GB
Fits Get file →
IQ3_XXS2.8 GB 4.3 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
IQ3_S3.1 GB 4.6 GB
Fits Get file →
Q3_K_S3.1 GB 4.6 GB
Fits Get file →
IQ3_M3.4 GB 5.0 GB
Fits Get file →
Q3_K_M3.7 GB 5.2 GB
Fits Get file →
IQ4_XS3.7 GB 5.3 GB
Fits Get file →
IQ4_NL4.0 GB 5.5 GB
Fits Get file →
Q4_04.0 GB 5.5 GB
Fits Get file →
Q3_K_L4.0 GB 5.5 GB
Fits Get file →
Q4_K_S4.0 GB 5.6 GB
Fits Get file →
Q4_14.4 GB 5.9 GB
Fits Get file →
Q4_K_M4.4 GB 6.0 GB
Fits Get file →
Q5_K_S4.8 GB 6.4 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.7 GB 7.2 GB
Tight Get file →

For 8 GB VRAM, use IQ1_S (1.58 GB, 6.4 GB memory) or IQ1_M (1.71 GB, 6.5 GB memory). If 12 GB VRAM is available, IQ2_S (2.25 GB, 7 GB memory) or Q2_K (2.67 GB, 7.5 GB memory) are good choices. Larger VRAM allows higher‑quality quants such as Q5_K_M (5.14 GB, 9.9 GB memory).

What GPU do you need for Cerebras OPT Fusion i1?

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_S (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 10.5 GB in use).

Which Cerebras OPT Fusion i1 quant should you choose?

Q4_K_M is the usual starting point for Cerebras OPT Fusion i1: it balances file size and quality well. Here it is a 4.4 GB file.

If memory is tight, the smallest file is IQ1_S at 1.6 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

Architecturegpt2
Parameters6.86B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyCerebras
Licensemit
Downloads (HF)984
Last updated2025-03-05

Frequently asked questions about Cerebras OPT Fusion i1

How much VRAM does Cerebras OPT Fusion i1 need?

About 9.2 GB at Q4_K_M with an 8K context window. That is the 4.4 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 Cerebras OPT Fusion i1 on an 8 GB GPU?

Yes, with IQ3_S: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Cerebras OPT Fusion i1 GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.7 GB, IQ2_XXS is 1.9 GB, IQ2_XS is 2.1 GB, IQ2_S is 2.2 GB, IQ2_M is 2.4 GB and 18 more.

What context length does Cerebras OPT Fusion i1 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 Cerebras OPT Fusion i1 GGUF?

The files are on Hugging Face in the mradermacher/Cerebras-OPT-Fusion-i1-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 Cerebras OPT Fusion i1 use?

Hugging Face lists the license as mit. 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 this model on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations, which require about 6.4–6.5 GB of VRAM at 8k context.

Does the model support image input?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the MIT license.

Other GGUFs of Cerebras-OPT-Fusion

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Cerebras models

All Cerebras →

Other small models

All small models →