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 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.
GLM 4.5 Iceblink v3 106B A12B – 107B parameter LLM with 12B active experts
GLM 4.5 Iceblink v3 106B A12B is a 107B parameter language model built on the glm4moe architecture. It contains 12B active parameters in a mixture of experts and supports a context length of 131072 tokens. The model is released under the MIT license.
Good at
- Large context handling
- Mixture of experts for specialized tasks
- Roleplay capabilities
Limits
- Requires high VRAM for full precision
- No vision support
- Limited language set (languages list empty)
Best for
- Long‑form content generation
- Complex dialogue simulations
- Research prototyping
Who it’s for. Developers and researchers needing a large‑scale LLM with extensive context and expert specialization. Suitable for environments with sufficient GPU memory and a need for roleplay or dialogue tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 43.6 GB | 45.6 GB | Too big | Get file → | |
| Q3_K_S | 50.7 GB | 52.7 GB | Too big | Get file → | |
| Q3_K_M | 55.3 GB | 57.3 GB | Too big | Get file → | |
| Q3_K_L | 57.6 GB | 59.7 GB | Too big | Get file → | |
| IQ4_XS | 58.7 GB | 60.7 GB | Too big | Get file → | |
| Q4_K_S | 64.7 GB | 66.8 GB | Too big | Get file → | |
| Q4_K_M | 70.4 GB | 72.5 GB | Too big | Get file → | |
| Q5_K_S | 75.7 GB | 77.8 GB | Too big | Get file → | |
| Q5_K_M | 80.6 GB | 82.7 GB | Too big | Get file → | |
| Q6_K | 95.9 GB | 97.9 GB | Too big | Get file → | |
| Q8_0 | 113.6 GB | 115.7 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (43.6 GB file, 45.6 GB memory at 8K context). For 16 GB VRAM, Q3_K_S (50.71 GB file, 52.7 GB memory) or Q3_K_M (55.28 GB file, 57.3 GB memory). For 24 GB VRAM, Q4_K_S (64.74 GB file, 66.8 GB memory) or Q4_K_M (70.45 GB file, 72.5 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: 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 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.
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
Source
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?
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 GLM 4.5 Iceblink v3 106B A12B 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 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-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 GLM 4.5 Iceblink v3 106B A12B on 8 GB VRAM?
Only with the Q2_K quant, which requires about 45.6 GB of VRAM at 8K context, so 8 GB VRAM is insufficient.
Does this model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the MIT license.