KI

Kimi K2 Instruct 0905 THIREUS IQ3 S R4 SPECIAL SPLIT

KimiGGUF by ThireusUpdated 2026-02-12
Download on Hugging Face
Parameters1000B
Context256K
Layers61
Architecturedeepseek2
Smallest quant441.7 GB
Quick answer

Kimi K2 Instruct 0905 THIREUS IQ3 S R4 SPECIAL SPLIT needs about 443.3 GB of memory at IQ3_S (a 441.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Kimi K2 Instruct 0905 THIREUS IQ3 S R4 SPECIAL SPLIT is a 1000B-parameter Kimi model in GGUF format, quantized by Thireus. Its trained context length is 256K tokens. The repository has 1 quant file, from 441.7 GB (IQ3_S) to 441.7 GB (IQ3_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_S441.7 GB (1097 parts) 443.3 GB
Too big Get file →

What GPU do you need for Kimi K2 Instruct 0905 THIREUS IQ3 S R4 SPECIAL SPLIT?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Kimi K2 Instruct 0905 THIREUS IQ3 S R4 SPECIAL SPLIT quant should you choose?

IQ3_S (441.7 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2
Parameters1000B (approximate, mixture of experts)
Layers61
Trained context262,144 tokens
KV cache (fp16)130 KB per token

Source

Quantized byThireus
FamilyKimi
Licensemit
Downloads (HF)53
Last updated2026-02-12

Frequently asked questions about Kimi K2 Instruct 0905 THIREUS IQ3 S R4 SPECIAL SPLIT

How much VRAM does Kimi K2 Instruct 0905 THIREUS IQ3 S R4 SPECIAL SPLIT need?

About 443.3 GB at IQ3_S with an 8K context window. That is the 441.7 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 Kimi K2 Instruct 0905 THIREUS IQ3 S R4 SPECIAL SPLIT on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 443.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kimi K2 Instruct 0905 THIREUS IQ3 S R4 SPECIAL SPLIT GGUF?

It depends on the quant: IQ3_S is 441.7 GB.

What context length does Kimi K2 Instruct 0905 THIREUS IQ3 S R4 SPECIAL SPLIT support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Kimi K2 Instruct 0905 THIREUS IQ3 S R4 SPECIAL SPLIT GGUF?

The files are on Hugging Face in the Thireus/Kimi-K2-Instruct-0905-THIREUS-IQ3_S_R4-SPECIAL_SPLIT repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Kimi K2 Instruct 0905 THIREUS IQ3 S R4 SPECIAL SPLIT 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 Thireus

All by Thireus →

More Kimi models

All Kimi →

Other large models

All large models →