DE

Derestricted Iceblink

DerestrictedGGUF by mradermacherUpdated 2026-10-27
Download on Hugging Face
Parameters107B
Context128K
Layers46
Architectureglm4moe
Smallest quant43.6 GB
Quick answer

Derestricted Iceblink needs about 72.5 GB of memory at Q4_K_M (a 70.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 11 quants, from 43.6 GB (Q2_K) to 113.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.2 GB.

Derestricted Iceblink is a 107B-parameter Derestricted model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 11 quant files, from 43.6 GB (Q2_K) to 113.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K43.6 GB 45.6 GB
Too big Get file →
Q3_K_S50.7 GB 52.7 GB
Too big Get file →
Q3_K_M55.3 GB 57.3 GB
Too big Get file →
Q3_K_L57.6 GB 59.7 GB
Too big Get file →
IQ4_XS58.7 GB 60.7 GB
Too big Get file →
Q4_K_S64.7 GB 66.8 GB
Too big Get file →
Q4_K_M70.4 GB 72.5 GB
Too big Get file →
Q5_K_S75.7 GB 77.8 GB
Too big Get file →
Q5_K_M80.6 GB 82.7 GB
Too big Get file →
Q6_K95.9 GB 97.9 GB
Too big Get file →
Q8_0113.6 GB 115.7 GB
Too big Get file →

What GPU do you need for Derestricted Iceblink?

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: the best quant that fits is Q2_K (43.6 GB file, about 45.6 GB in use).

Which Derestricted Iceblink quant should you choose?

Q4_K_M is the usual starting point for Derestricted Iceblink: it balances file size and quality well. Here it is a 70.4 GB file.

The Q8_0 file is 113.6 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 43.6 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

Architectureglm4moe
Parameters107B (approximate, mixture of experts)
Layers46
Trained context131,072 tokens
KV cache (fp16)184 KB per token

Source

Quantized bymradermacher
Licensemit
Downloads (HF)282
Last updated2026-10-27

Frequently asked questions about Derestricted Iceblink

How much VRAM does Derestricted Iceblink need?

About 72.5 GB at Q4_K_M with an 8K context window. That is the 70.4 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 Derestricted Iceblink on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 45.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Derestricted Iceblink GGUF?

It depends on the quant: Q2_K is 43.6 GB, Q3_K_S is 50.7 GB, Q3_K_M is 55.3 GB, Q3_K_L is 57.6 GB, IQ4_XS is 58.7 GB, Q4_K_S is 64.7 GB and 5 more.

What context length does Derestricted Iceblink support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.5 GB at 8K and 6.2 GB at 32K.

Where can I download Derestricted Iceblink GGUF?

The files are on Hugging Face in the mradermacher/derestricted-iceblink-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 Derestricted Iceblink 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 Derestricted models

All Derestricted →

Other large models

All large models →