GP

Mikivis gpt2 large imdb3

GptGGUF by tensorblockUpdated 2026-01-27
Download on Hugging Face
Parameters838M
Context1K
Layers36
Architecturegpt2
Smallest quant0.3 GB
Quick answer

Mikivis gpt2 large imdb3 needs about 2.4 GB of memory at Q2_K (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Fine‑tuned GPT‑2 large for IMDb movie reviews

Mikivis gpt2 large imdb3 is a 0.838 B parameter GPT‑2 model trained on a custom IMDb dataset. The model is quantized to Q2_K and is compatible with llama.cpp. It supports a 1024‑token context window and is released under the Apache‑2.0 license.

Good at

  • Movie review generation
  • Sentiment‑aware text completion
  • Lightweight inference

Limits

  • No vision support
  • Limited to 1024‑token context
  • Requires 2.4 GB VRAM at 8 k context

Best for

  • Generating movie reviews
  • Fine‑tuning on small text corpora
  • Running on low‑VRAM GPUs

Who it’s for. Developers needing a compact GPT‑2 variant for movie‑review tasks. The model is ideal for applications that require quick inference on modest hardware while maintaining reasonable accuracy on sentiment‑rich text.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.3 GB 1.0 GB
Fits Get file →

The only available quant is Q2_K, with a 0.35 GB file size. It requires roughly 2.4 GB VRAM when running with an 8 k context. For 8 GB VRAM systems, this quant is suitable; for 4 GB VRAM, it may still fit if the context is reduced.

What GPU do you need for Mikivis gpt2 large imdb3?

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 Q2_K (0.3 GB file, about 2.4 GB in use).

Which Mikivis gpt2 large imdb3 quant should you choose?

Q2_K (0.3 GB) is the middle option in this repository. 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
Parameters838M
Layers36
Trained context1,024 tokens
KV cache (fp16)180 KB per token

Source

Quantized bytensorblock
FamilyGpt
Licenseapache-2.0
Downloads (HF)587
Last updated2026-01-27

Frequently asked questions about Mikivis gpt2 large imdb3

How much VRAM does Mikivis gpt2 large imdb3 need?

About 2.4 GB at Q2_K with an 8K context window. That is the 0.3 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 Mikivis gpt2 large imdb3 on an 8 GB GPU?

Yes, with Q2_K: the 0.3 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mikivis gpt2 large imdb3 GGUF?

It depends on the quant: Q2_K is 0.3 GB.

What context length does Mikivis gpt2 large imdb3 support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 1.5 GB at 8K and 0.2 GB at 1K.

Where can I download Mikivis gpt2 large imdb3 GGUF?

The files are on Hugging Face in the tensorblock/Mikivis_gpt2-large-imdb3-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 Mikivis gpt2 large imdb3 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 this model on 8 GB VRAM?

Yes, the Q2_K quant requires about 2.4 GB VRAM at 8 k context, well within an 8 GB budget.

What context length does it support?

The model was trained with a 1024‑token context and works best with that limit.

Is this model vision‑capable?

No, it is a text‑only GPT‑2 model with no vision support.

Similar models

Browse all →

More from tensorblock

All by tensorblock →

More Gpt models

All Gpt →

Other tiny models

All tiny models →