EV

EventTwin

EventtwinGGUF by mradermacherUpdated 2026-10-21
Download on Hugging Face
Parameters568M
Context8K
Layers24
Architecturebert
Smallest quant0.4 GB
Quick answer

EventTwin needs about 1.7 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.4 GB (Q2_K) to 1.2 GB (F16).

EventTwin v2.6 – Chinese event coreference model

EventTwin v2.6 judges whether two Chinese event‑mention frames refer to the same real‑world event. It outputs a logit difference (ld) and routes decisions based on calibrated thresholds. The model is trained on full‑length input with a context size of 8192 tokens.

Good at

  • Cross‑document event coreference
  • Full‑length Chinese event frames
  • Threshold‑based decision routing

Limits

  • No vision support
  • Requires full‑length input
  • Apache‑2.0 license

Best for

  • News clustering pipelines
  • Event‑based analytics
  • Automated event merging

Who it’s for. Engineers and researchers building Chinese news clustering or event analytics systems. The model is suitable for applications that need precise event‑coreference decisions with calibrated thresholds.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.4 GB 1.7 GB
Fits Get file →
Q3_K_S0.4 GB 1.7 GB
Fits Get file →
Q3_K_M0.4 GB 1.7 GB
Fits Get file →
IQ4_XS0.4 GB 1.7 GB
Fits Get file →
Q3_K_L0.4 GB 1.7 GB
Fits Get file →
Q4_K_S0.4 GB 1.7 GB
Fits Get file →
Q4_K_M0.4 GB 1.7 GB
Fits Get file →
Q5_K_S0.5 GB 1.8 GB
Fits Get file →
Q5_K_M0.5 GB 1.8 GB
Fits Get file →
Q6_K0.5 GB 1.8 GB
Fits Get file →
Q8_00.6 GB 1.9 GB
Fits Get file →
F161.2 GB 2.5 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_S (0.42 GB) or Q4_K_M (0.44 GB). For 4 GB VRAM, Q2_K (0.37 GB) or Q3_K_S (0.38 GB) are suitable. Higher‑precision quants like F16 (1.16 GB) require more memory but give the most accurate ld values.

What GPU do you need for EventTwin?

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 (1.2 GB file, about 2.5 GB in use).

Which EventTwin quant should you choose?

Q4_K_M is the usual starting point for EventTwin: it balances file size and quality well. Here it is a 0.4 GB file.

The Q8_0 file is 0.6 GB, about 1.5 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 0.4 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

Architecturebert
Parameters568M
Layers24
Trained context8,192 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilyEventtwin
Licenseapache-2.0
Downloads (HF)1,304
Last updated2026-10-21

Frequently asked questions about EventTwin

How much VRAM does EventTwin need?

About 1.7 GB at Q4_K_M with an 8K context window. That is the 0.4 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 EventTwin on an 8 GB GPU?

Yes, with F16: the 1.2 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of EventTwin GGUF?

It depends on the quant: Q2_K is 0.4 GB, Q3_K_S is 0.4 GB, Q3_K_M is 0.4 GB, IQ4_XS is 0.4 GB, Q3_K_L is 0.4 GB, Q4_K_S is 0.4 GB and 6 more.

What context length does EventTwin support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.8 GB at 8K.

Where can I download EventTwin GGUF?

The files are on Hugging Face in the mradermacher/EventTwin-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 EventTwin 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 EventTwin on 8 GB VRAM?

Yes, use Q4_K_S or Q4_K_M quant files; they fit within 8 GB VRAM with approximate memory usage of 1.7 GB at 8k context.

Does EventTwin support English text?

The model is trained on Chinese event‑mention frames and is not designed for English input.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other tiny models

All tiny models →