IC

Iceblink v2 SFT v2 2 i1

IceblinkGGUF by mradermacherUpdated 2025-12-04
Download on Hugging Face
Parameters110B
Context128K
Layers—
Architectureglm4moe
Smallest quant0.2 GB
Quick answer

Iceblink v2 SFT v2 2 i1 needs about 50.9 GB of memory at Q2_K (a 45.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 0.2 GB to 49.8 GB (IQ3_XS).

Iceblink v2 SFT v2 2 i1 is a 110B-parameter Iceblink model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 3 quant files, from 0.2 GB to 49.8 GB (IQ3_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 0.8 GB
Fits Get file →
Q2_K45.0 GB 50.9 GB
Too big Get file →
IQ3_XS49.8 GB 56.2 GB
Too big Get file →

What GPU do you need for Iceblink v2 SFT v2 2 i1?

These figures add the file size, an fp16 KV cache at an 8K context window 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 the main file (0.2 GB file, about 0.8 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.8 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.8 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.8 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.8 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.8 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.8 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.8 GB in use).

Which Iceblink v2 SFT v2 2 i1 quant should you choose?

Q2_K (45.0 GB) is the middle option in this repository. 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.

If memory is tight, the smallest file is the first one in the table at 0.2 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

Architectureglm4moe
Parameters110B
Trained context131,072 tokens

Source

Quantized bymradermacher
FamilyIceblink
Downloads (HF)25
Last updated2025-12-04

Frequently asked questions about Iceblink v2 SFT v2 2 i1

How much VRAM does Iceblink v2 SFT v2 2 i1 need?

About 50.9 GB at Q2_K with an 8K context window. That is the 45.0 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 Iceblink v2 SFT v2 2 i1 on an 8 GB GPU?

Yes, with the smaller files: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Iceblink v2 SFT v2 2 i1 GGUF?

It depends on the quant: file is 0.2 GB, Q2_K is 45.0 GB, IQ3_XS is 49.8 GB.

What context length does Iceblink v2 SFT v2 2 i1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K).

Where can I download Iceblink v2 SFT v2 2 i1 GGUF?

The files are on Hugging Face in the mradermacher/Iceblink-v2-SFT-v2-2-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Iceblink models

All Iceblink →

Other large models

All large models →