SE

Sequential_Helium_6B

SequentialGGUF by mradermacherUpdated 2026-05-26
Download on Hugging Face
Parameters6.3B
Context4K
Layers32
Architecturellama
Smallest quant0.0 GB
Quick answer

Sequential_Helium_6B needs about 5.4 GB of memory at Q4_K_M (a 3.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 5.2 GB (Q6_K).

Sequential_Helium_6B – 6.3B parameter Llama model trained on temporally ordered data

Sequential_Helium_6B is a 6.3B parameter decoder‑only Llama model. It was trained with sequential pretraining on temporally ordered Common Crawl data to improve factuality on recent knowledge. The model is released under CC‑BY‑SA‑4.0 and is not aligned for instruction following or chat.

Good at

  • Factual responses on recent events
  • Temporal reasoning
  • Multilingual support in many European languages

Limits

  • Not aligned – may produce biased or harmful content
  • No instruction tuning – limited chat capability
  • Requires 4096 token context

Best for

  • Research on temporal pretraining
  • Benchmarking with KairosQA
  • Generating temporally grounded text

Who it’s for. Researchers and developers interested in the effects of sequential pretraining on factuality and temporal reasoning. The model is suitable for experimentation and downstream fine‑tuning but not for production chat applications without additional alignment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.0 GB
Fits Get file →
IQ1_S1.5 GB 2.5 GB
Fits Get file →
IQ1_M1.6 GB 2.7 GB
Fits Get file →
IQ2_XXS1.8 GB 2.8 GB
Fits Get file →
IQ2_XS2.0 GB 3.0 GB
Fits Get file →
IQ2_S2.1 GB 3.1 GB
Fits Get file →
IQ2_M2.3 GB 3.3 GB
Fits Get file →
Q2_K_S2.3 GB 3.3 GB
Fits Get file →
Q2_K2.4 GB 3.5 GB
Fits Get file →
IQ3_XXS2.5 GB 3.5 GB
Fits Get file →
IQ3_XS2.7 GB 3.7 GB
Fits Get file →
Q3_K_S2.8 GB 3.8 GB
Fits Get file →
IQ3_S2.8 GB 3.9 GB
Fits Get file →
IQ3_M2.9 GB 4.0 GB
Fits Get file →
Q3_K_M3.1 GB 4.1 GB
Fits Get file →
Q3_K_L3.4 GB 4.4 GB
Fits Get file →
IQ4_XS3.4 GB 4.5 GB
Fits Get file →
Q4_03.6 GB 4.7 GB
Fits Get file →
IQ4_NL3.6 GB 4.7 GB
Fits Get file →
Q4_K_S3.6 GB 4.7 GB
Fits Get file →
Q4_K_M3.8 GB 4.9 GB
Fits Get file →
Q4_14.0 GB 5.0 GB
Fits Get file →
Q5_K_S4.4 GB 5.4 GB
Fits Get file →
Q5_K_M4.5 GB 5.5 GB
Fits Get file →
Q6_K5.2 GB 6.2 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (1.5 GB, 3.1 GB memory) or IQ1_M (1.62 GB, 3.2 GB memory). If 12 GB VRAM is available, Q2_K (2.43 GB, 4 GB memory) or Q3_K_M (3.11 GB, 4.7 GB memory) provide a good balance of size and performance. Higher‑quality quants such as Q4_K_M (3.82 GB, 5.4 GB memory) require 16 GB or more.

What GPU do you need for Sequential_Helium_6B?

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 (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K_M (4.5 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.2 GB file, about 6.7 GB in use).

Which Sequential_Helium_6B quant should you choose?

Q4_K_M is the usual starting point for Sequential_Helium_6B: it balances file size and quality well. Here it is a 3.8 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.3B
Layers32
Trained context4,096 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
Downloads (HF)746
Last updated2026-05-26

Frequently asked questions about Sequential_Helium_6B

How much VRAM does Sequential_Helium_6B need?

About 5.4 GB at Q4_K_M with an 8K context window. That is the 3.8 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 Sequential_Helium_6B on an 8 GB GPU?

Yes, with Q6_K: the 5.2 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sequential_Helium_6B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 1.5 GB, IQ1_M is 1.6 GB, IQ2_XXS is 1.8 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.1 GB and 19 more.

What context length does Sequential_Helium_6B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.

Where can I download Sequential_Helium_6B GGUF?

The files are on Hugging Face in the mradermacher/Sequential_Helium_6B-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 Sequential_Helium_6B use?

Hugging Face lists the license as cc-by-sa-4.0. 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 Sequential_Helium_6B on 8 GB VRAM?

Yes, with the IQ1_S or IQ1_M quant, which use about 3.1–3.2 GB of VRAM at 8 k context.

Does the model support vision or audio?

No, it is a text‑only language model.

Is the model aligned for safe use?

No, it is a base model and may generate biased or harmful content without further alignment.

Other GGUFs of Sequential_Helium_6B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sequential models

All Sequential →

Other small models

All small models →