DI

Diff Llm

DiffGGUF by mradermacherUpdated 2025-12-25
Download on Hugging Face
Parameters8.02B
Context4K
Layers32
Architecturellada
Smallest quant0.0 GB
Quick answer

Diff Llm needs about 9.7 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 6.6 GB (Q6_K).

Diff Llm is a 8.02B-parameter Diff model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 25 quant files, from 0.0 GB to 6.6 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S2.0 GB 4.7 GB
Fits Get file →
IQ1_M2.2 GB 4.8 GB
Fits Get file →
IQ2_XXS2.4 GB 5.0 GB
Fits Get file →
IQ2_XS2.6 GB 5.2 GB
Fits Get file →
IQ2_S2.8 GB 5.4 GB
Fits Get file →
Q2_K_S2.9 GB 5.6 GB
Fits Get file →
IQ2_M3.0 GB 5.6 GB
Fits Get file →
Q2_K3.2 GB 5.8 GB
Fits Get file →
IQ3_XXS3.2 GB 5.9 GB
Fits Get file →
IQ3_XS3.5 GB 6.1 GB
Fits Get file →
IQ3_S3.7 GB 6.3 GB
Fits Get file →
Q3_K_S3.7 GB 6.3 GB
Fits Get file →
IQ3_M3.8 GB 6.5 GB
Fits Get file →
Q3_K_M4.0 GB 6.7 GB
Fits Get file →
Q3_K_L4.3 GB 7.0 GB
Fits Get file →
IQ4_XS4.4 GB 7.1 GB
Fits Get file →
IQ4_NL4.6 GB 7.3 GB
Tight Get file →
Q4_04.7 GB 7.3 GB
Tight Get file →
Q4_K_S4.7 GB 7.3 GB
Tight Get file →
Q4_K_M4.9 GB 7.6 GB
Tight Get file →
Q4_15.1 GB 7.8 GB
Tight Get file →
Q5_K_S5.6 GB 8.2 GB
Too big Get file →
Q5_K_M5.7 GB 8.4 GB
Too big Get file →
Q6_K6.6 GB 9.2 GB
Too big Get file →

What GPU do you need for Diff Llm?

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: the best quant that fits is the main file (0.0 GB file, about 4.8 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_XXS (3.2 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 11.4 GB in use).

Which Diff Llm quant should you choose?

Q4_K_M is the usual starting point for Diff Llm: it balances file size and quality well. Here it is a 4.9 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

Architecturellada
Parameters8.02B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyDiff
Licensemit
Downloads (HF)455
Last updated2025-12-25

Frequently asked questions about Diff Llm

How much VRAM does Diff Llm need?

About 9.7 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Diff Llm on an 8 GB GPU?

Yes, with IQ3_XXS: the 3.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Diff Llm GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB and 19 more.

What context length does Diff Llm support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download Diff Llm GGUF?

The files are on Hugging Face in the mradermacher/Diff-llm-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 Diff Llm 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.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Diff models

All Diff →

Other small models

All small models →