GL

GLM 4.5 Iceblink v3 106B A12B

GLMGGUF by mradermacherUpdated 2026-03-12
Download on Hugging Face
Parameters107B
Context128K
Layers46
Architectureglm4moe
Smallest quant0.2 GB
Quick answer

GLM 4.5 Iceblink v3 106B A12B 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 24 quants, from 0.2 GB to 95.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.2 GB.

GLM 4.5 Iceblink v3 106B A12B – a 106B parameter mixture of experts model

GLM 4.5 Iceblink v3 106B A12B is a 106B parameter model with 12B active parameters in a mixture of experts architecture. It supports a 131072 token context window and is released under the MIT license. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Mixture of experts efficiency
  • Roleplay capabilities

Limits

  • No vision support
  • Large memory requirement
  • Requires GGUF format

Best for

  • Long-form content generation
  • Complex dialogue systems
  • Research on MoE models

Who it’s for. Developers and researchers who need a large language model with extensive context and mixture of experts. The model is suitable for applications that can handle the high memory demands and are built around the GGUF format.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 2.3 GB
Fits Get file →
IQ1_S33.9 GB 35.9 GB
Too big Get file →
IQ1_M35.5 GB 37.6 GB
Too big Get file →
IQ2_XXS38.2 GB 40.3 GB
Too big Get file →
IQ2_XS40.5 GB 42.5 GB
Too big Get file →
IQ2_S40.9 GB 42.9 GB
Too big Get file →
IQ2_M43.0 GB 45.1 GB
Too big Get file →
Q2_K43.6 GB 45.6 GB
Too big Get file →
Q2_K_S43.7 GB 45.8 GB
Too big Get file →
IQ3_XXS47.2 GB 49.3 GB
Too big Get file →
IQ3_XS48.2 GB 50.2 GB
Too big Get file →
Q3_K_S50.7 GB 52.7 GB
Too big Get file →
IQ3_S50.7 GB 52.8 GB
Too big Get file →
IQ3_M51.4 GB 53.5 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_XS58.1 GB 60.2 GB
Too big Get file →
Q4_060.5 GB 62.6 GB
Too big Get file →
Q4_K_S64.7 GB 66.8 GB
Too big Get file →
Q4_167.0 GB 69.0 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 →

For limited VRAM, choose the smallest quant: IQ1_S (33.89 GB file, 35.9 GB memory at 8k context). If you have more memory, Q4_0 (60.55 GB file, 62.6 GB memory) offers higher quality. For the lowest memory footprint, use the unknown quant (0.23 GB file, 2.3 GB memory).

What GPU do you need for GLM 4.5 Iceblink v3 106B A12B?

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: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q2_K_S (43.7 GB file, about 45.8 GB in use).

Which GLM 4.5 Iceblink v3 106B A12B quant should you choose?

Q4_K_M is the usual starting point for GLM 4.5 Iceblink v3 106B A12B: it balances file size and quality well. Here it is a 70.4 GB file.

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
Parameters107B (approximate, mixture of experts)
Active parameters12B
Layers46
Trained context131,072 tokens
KV cache (fp16)184 KB per token

Source

Quantized bymradermacher
FamilyGLM
Licensemit
Downloads (HF)1,719
Last updated2026-03-12

Frequently asked questions about GLM 4.5 Iceblink v3 106B A12B

How much VRAM does GLM 4.5 Iceblink v3 106B A12B 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 GLM 4.5 Iceblink v3 106B A12B on an 8 GB GPU?

Yes, with the smaller files: the 0.2 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GLM 4.5 Iceblink v3 106B A12B GGUF?

It depends on the quant: file is 0.2 GB, IQ1_S is 33.9 GB, IQ1_M is 35.5 GB, IQ2_XXS is 38.2 GB, IQ2_XS is 40.5 GB, IQ2_S is 40.9 GB and 18 more.

What context length does GLM 4.5 Iceblink v3 106B A12B 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 GLM 4.5 Iceblink v3 106B A12B GGUF?

The files are on Hugging Face in the mradermacher/GLM-4.5-Iceblink-v3-106B-A12B-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 GLM 4.5 Iceblink v3 106B A12B 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.

Can I run this model on 8 GB VRAM?

No, the smallest quant requires 2.3 GB memory at 8k context, but the file size is 0.23 GB. However, the model still needs more VRAM for inference.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the MIT license.

Other GGUFs of GLM-4.5-Iceblink-v3-106B-A12B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More GLM models

All GLM →

Other large models

All large models →