BI

Big Alice 28B v1

BigGGUF by mradermacherUpdated 2025-05-17
Download on Hugging Face
Parameters28.6B
Context64K
Layers100
Architecturellama
Smallest quant6.5 GB
Quick answer

Big Alice 28B v1 needs about 21.1 GB of memory at Q4_K_M (a 17.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 23 quants, from 6.5 GB (IQ1_S) to 23.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 13.4 GB.

Big Alice 28B v1 is a 28.6B-parameter Big model in GGUF format, quantized by mradermacher. Its trained context length is 64K tokens. The repository has 23 quant files, from 6.5 GB (IQ1_S) to 23.5 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S6.5 GB 10.3 GB
Too big Get file →
IQ1_M7.0 GB 10.9 GB
Too big Get file →
IQ2_XXS7.9 GB 11.8 GB
Too big Get file →
IQ2_XS8.8 GB 12.6 GB
Too big Get file →
IQ2_S9.2 GB 13.1 GB
Too big Get file →
IQ2_M9.9 GB 13.8 GB
Too big Get file →
Q2_K_S10.1 GB 13.9 GB
Too big Get file →
Q2_K10.8 GB 14.7 GB
Too big Get file →
IQ3_XXS11.2 GB 15.1 GB
Too big Get file →
IQ3_XS12.0 GB 15.9 GB
Too big Get file →
Q3_K_S12.6 GB 16.4 GB
Too big Get file →
IQ3_S12.6 GB 16.5 GB
Too big Get file →
IQ3_M13.0 GB 16.9 GB
Too big Get file →
Q3_K_M13.9 GB 17.8 GB
Too big Get file →
Q3_K_L15.1 GB 19.0 GB
Too big Get file →
IQ4_XS15.5 GB 19.3 GB
Too big Get file →
Q4_016.3 GB 20.2 GB
Too big Get file →
Q4_K_S16.4 GB 20.2 GB
Too big Get file →
Q4_K_M17.3 GB 21.1 GB
Too big Get file →
Q4_118.0 GB 21.9 GB
Too big Get file →
Q5_K_S19.8 GB 23.6 GB
Too big Get file →
Q5_K_M20.3 GB 24.1 GB
Too big Get file →
Q6_K23.5 GB 27.3 GB
Too big Get file →

What GPU do you need for Big Alice 28B v1?

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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ2_XXS (7.9 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XS (12.0 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_S (19.8 GB file, about 23.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (23.5 GB file, about 27.3 GB in use).

Which Big Alice 28B v1 quant should you choose?

Q4_K_M is the usual starting point for Big Alice 28B v1: it balances file size and quality well. Here it is a 17.3 GB file.

If memory is tight, the smallest file is IQ1_S at 6.5 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

Architecturellama
Parameters28.6B
Layers100
Trained context65,536 tokens
KV cache (fp16)400 KB per token

Source

Quantized bymradermacher
FamilyBig
Licensemit
Downloads (HF)155
Last updated2025-05-17

Frequently asked questions about Big Alice 28B v1

How much VRAM does Big Alice 28B v1 need?

About 21.1 GB at Q4_K_M with an 8K context window. That is the 17.3 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 Big Alice 28B v1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Big Alice 28B v1 GGUF?

It depends on the quant: IQ1_S is 6.5 GB, IQ1_M is 7.0 GB, IQ2_XXS is 7.9 GB, IQ2_XS is 8.8 GB, IQ2_S is 9.2 GB, IQ2_M is 9.9 GB and 17 more.

What context length does Big Alice 28B v1 support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 3.4 GB at 8K and 13.4 GB at 32K.

Where can I download Big Alice 28B v1 GGUF?

The files are on Hugging Face in the mradermacher/Big-Alice-28B-v1-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 Big Alice 28B v1 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.

Other GGUFs of Big-Alice-28B-v1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Big models

All Big →

Other medium models

All medium models →