GLM 4.5 Architect 106B A12B needs about 74.9 GB of memory at Q4_K_M (a 72.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 15 quants, from 0.2 GB to 99.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.
GLM 4.5 Architect 106B A12B – 110B parameter LLM with 12B active experts
GLM 4.5 Architect 106B A12B is a 110B parameter model with 12B active mixture‑of‑experts. It was finetuned on back‑translated short story anthologies for 8 epochs. The model supports reasoning and tool usage.
Good at
- Reasoning
- Tool usage
- Long‑form prose generation
Limits
- Large VRAM requirement
- No vision support
- MIT license only
Best for
- Writing assistance
- Complex reasoning tasks
- Tool‑integrated workflows
Who it’s for. Developers needing a large language model with expert‑mixing capability for text generation and reasoning. Suitable for research or production environments with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 2.3 GB | Fits | Get file → | |
| Q2_K | 45.0 GB | 47.0 GB | Too big | Get file → | |
| Q3_K_S | 52.4 GB | 54.4 GB | Too big | Get file → | |
| IQ3_S | 52.4 GB | 54.5 GB | Too big | Get file → | |
| IQ3_M | 53.1 GB | 55.2 GB | Too big | Get file → | |
| Q3_K_M | 57.0 GB | 59.1 GB | Too big | Get file → | |
| Q3_K_L | 59.4 GB | 61.5 GB | Too big | Get file → | |
| IQ4_XS | 60.1 GB | 62.1 GB | Too big | Get file → | |
| Q4_0 | 62.6 GB | 64.7 GB | Too big | Get file → | |
| Q4_K_S | 66.9 GB | 68.9 GB | Too big | Get file → | |
| Q4_1 | 69.3 GB | 71.3 GB | Too big | Get file → | |
| Q4_K_M | 72.9 GB | 74.9 GB | Too big | Get file → | |
| Q5_K_S | 78.3 GB | 80.3 GB | Too big | Get file → | |
| Q5_K_M | 83.4 GB | 85.5 GB | Too big | Get file → | |
| Q6_K | 99.0 GB | 101.1 GB | Too big | Get file → |
For 8 GB VRAM use the Q2_K quant (file size 44.97 GB, estimated 47 GB memory at 8 k context). For 16 GB VRAM the Q3_K_S quant (52.36 GB, 54.4 GB memory) is appropriate. Higher quants such as Q4_K_M or Q5_K_M require 24 GB or more.
What GPU do you need for GLM 4.5 Architect 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 (45.0 GB file, about 47.0 GB in use).
Which GLM 4.5 Architect 106B A12B quant should you choose?
Q4_K_M is the usual starting point for GLM 4.5 Architect 106B A12B: it balances file size and quality well. Here it is a 72.9 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
Source
Frequently asked questions about GLM 4.5 Architect 106B A12B
How much VRAM does GLM 4.5 Architect 106B A12B need?
About 74.9 GB at Q4_K_M with an 8K context window. That is the 72.9 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 Architect 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 Architect 106B A12B GGUF?
It depends on the quant: file is 0.2 GB, Q2_K is 45.0 GB, Q3_K_S is 52.4 GB, IQ3_S is 52.4 GB, IQ3_M is 53.1 GB, Q3_K_M is 57.0 GB and 9 more.
What context length does GLM 4.5 Architect 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 1.6 GB at 8K and 6.3 GB at 32K.
Where can I download GLM 4.5 Architect 106B A12B GGUF?
The files are on Hugging Face in the mradermacher/GLM-4.5-Architect-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 Architect 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?
Use the Q2_K quant; it estimates 47 GB memory at 8 k context, which is above 8 GB but may work with lower context or CPU fallback.
Does this model support vision?
No, the model has no vision capabilities.
What license does it use?
The model is released under the MIT license.