GLM 4 T1 54B needs about 34.0 GB of memory at Q4_K_M (a 32.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 24 quants, from 0.0 GB to 44.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.
GLM 4 T1 54B – 54.2B parameter LLM in GGUF format
GLM 4 T1 54B is a 54.2B parameter model with a 32768 token context window. It supports reasoning and tool usage. The model is released under the MIT license and is available in multiple quantizations.
Good at
- Reasoning tasks
- Tool integration
- Large context handling
Limits
- No vision support
- Requires large VRAM for full precision
- No mixture of experts
Best for
- Complex reasoning workflows
- Tool‑enabled automation
- Long‑form content generation
Who it’s for. Developers and researchers needing a large language model with extensive context and reasoning capabilities. The model is suitable for applications that can accommodate its memory requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.4 GB | Fits | Get file → | |
| IQ1_S | 11.7 GB | 13.1 GB | Too big | Get file → | |
| IQ1_M | 12.8 GB | 14.2 GB | Too big | Get file → | |
| IQ2_XXS | 14.6 GB | 16.0 GB | Too big | Get file → | |
| IQ2_XS | 16.2 GB | 17.6 GB | Too big | Get file → | |
| IQ2_S | 17.0 GB | 18.4 GB | Too big | Get file → | |
| IQ2_M | 18.5 GB | 19.9 GB | Too big | Get file → | |
| Q2_K_S | 18.7 GB | 20.1 GB | Too big | Get file → | |
| Q2_K | 20.2 GB | 21.6 GB | Too big | Get file → | |
| IQ3_XXS | 21.1 GB | 22.4 GB | Too big | Get file → | |
| IQ3_XS | 22.5 GB | 23.8 GB | Too big | Get file → | |
| Q3_K_S | 23.7 GB | 25.0 GB | Too big | Get file → | |
| IQ3_S | 23.7 GB | 25.1 GB | Too big | Get file → | |
| IQ3_M | 24.5 GB | 25.8 GB | Too big | Get file → | |
| Q3_K_M | 26.3 GB | 27.7 GB | Too big | Get file → | |
| Q3_K_L | 28.5 GB | 29.9 GB | Too big | Get file → | |
| IQ4_XS | 29.1 GB | 30.5 GB | Too big | Get file → | |
| Q4_0 | 30.9 GB | 32.2 GB | Too big | Get file → | |
| Q4_K_S | 31.0 GB | 32.4 GB | Too big | Get file → | |
| Q4_K_M | 32.7 GB | 34.0 GB | Too big | Get file → | |
| Q4_1 | 34.1 GB | 35.5 GB | Too big | Get file → | |
| Q5_K_S | 37.4 GB | 38.8 GB | Too big | Get file → | |
| Q5_K_M | 38.4 GB | 39.8 GB | Too big | Get file → | |
| Q6_K | 44.5 GB | 45.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 11.74 GB, estimated memory 13.1 GB). For 16 GB VRAM, IQ2_XS (file size 16.21 GB, estimated memory 17.6 GB) or Q2_K (20.2 GB, 21.6 GB). For 32 GB VRAM, Q4_K_M (32.67 GB, 34 GB) or Q5_K_M (38.4 GB, 39.8 GB) provide higher quality. Estimates are approximate.
What GPU do you need for GLM 4 T1 54B?
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 (0.0 GB file, about 1.4 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.4 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.4 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.4 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_XXS (14.6 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is IQ3_XS (22.5 GB file, about 23.8 GB in use).
- 32 GB VRAM: the best quant that fits is IQ4_XS (29.1 GB file, about 30.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (44.5 GB file, about 45.9 GB in use).
Which GLM 4 T1 54B quant should you choose?
Q4_K_M is the usual starting point for GLM 4 T1 54B: it balances file size and quality well. Here it is a 32.7 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 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 T1 54B
How much VRAM does GLM 4 T1 54B need?
About 34.0 GB at Q4_K_M with an 8K context window. That is the 32.7 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 T1 54B on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GLM 4 T1 54B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 11.7 GB, IQ1_M is 12.8 GB, IQ2_XXS is 14.6 GB, IQ2_XS is 16.2 GB, IQ2_S is 17.0 GB and 18 more.
What context length does GLM 4 T1 54B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.5 GB at 32K.
Where can I download GLM 4 T1 54B GGUF?
The files are on Hugging Face in the mradermacher/GLM-4-T1-54B-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 T1 54B 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 T1 54B on 8 GB VRAM?
Use the IQ1_S quant which requires about 13.1 GB of VRAM at 8 k context. 8 GB is insufficient for full precision.
Does the model support vision tasks?
No, the model has no vision capability.
What license applies to this model?
The model is released under the MIT license.