Glm-4.6V needs about 72.6 GB of memory at Q4_K_M (a 70.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 36.8 GB (TQ1_0) to 213.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.2 GB.
GLM‑4.6V: 106B multimodal foundation model with 128k‑token context
GLM‑4.6V is a 106 billion‑parameter multimodal model that supports vision and native function calling. It was trained on 131 072 tokens and offers a 128 k‑token context window. The model is released under the MIT license and is available in multiple GGUF quantizations.
Good at
- Vision‑driven tool use
- Interleaved image‑text generation
- Large‑context reasoning
Limits
- Requires high VRAM for large quants
- No native audio or text‑only support beyond vision
- Limited to 128k context in practice
Best for
- Multimodal document analysis
- Vision‑based chatbot integration
- Complex image‑text content creation
Who it’s for. Developers building multimodal agents that need vision and function calling. Researchers requiring a large‑context, 106 B parameter model for cloud or high‑performance clusters.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 36.8 GB | 38.8 GB | Too big | Get file → | |
| IQ1_S | 37.0 GB | 39.1 GB | Too big | Get file → | |
| IQ1_M | 38.6 GB | 40.6 GB | Too big | Get file → | |
| IQ2_XXS | 41.2 GB | 43.2 GB | Too big | Get file → | |
| IQ2_M | 42.9 GB | 44.9 GB | Too big | Get file → | |
| Q2_K | 43.9 GB | 45.9 GB | Too big | Get file → | |
| Q2_K_L | 44.0 GB | 46.0 GB | Too big | Get file → | |
| Q2_K_XL | 45.8 GB | 47.8 GB | Too big | Get file → | |
| IQ3_XXS | 49.7 GB | 51.7 GB | Too big | Get file → | |
| Q3_K_S | 50.9 GB (2 parts) | 52.9 GB | Too big | Get file → | |
| Q3_K_XL | 52.7 GB (2 parts) | 54.8 GB | Too big | Get file → | |
| Q3_K_M | 55.4 GB (2 parts) | 57.5 GB | Too big | Get file → | |
| IQ4_XS | 58.3 GB (2 parts) | 60.4 GB | Too big | Get file → | |
| IQ4_NL | 60.6 GB (2 parts) | 62.6 GB | Too big | Get file → | |
| Q4_0 | 60.7 GB (2 parts) | 62.8 GB | Too big | Get file → | |
| Q4_K_S | 64.9 GB (2 parts) | 66.9 GB | Too big | Get file → | |
| Q4_K_XL | 65.5 GB (2 parts) | 67.5 GB | Too big | Get file → | |
| Q4_1 | 67.1 GB (2 parts) | 69.2 GB | Too big | Get file → | |
| Q4_K_M | 70.6 GB (2 parts) | 72.6 GB | Too big | Get file → | |
| Q5_K_S | 75.9 GB (2 parts) | 77.9 GB | Too big | Get file → | |
| Q5_K_XL | 80.3 GB (2 parts) | 82.3 GB | Too big | Get file → | |
| Q5_K_M | 80.8 GB (2 parts) | 82.8 GB | Too big | Get file → | |
| Q6_K | 95.9 GB (2 parts) | 97.9 GB | Too big | Get file → | |
| Q6_K_XL | 98.4 GB (2 parts) | 100.4 GB | Too big | Get file → | |
| Q8_0 | 113.6 GB (3 parts) | 115.7 GB | Too big | Get file → | |
| Q8_K_XL | 123.9 GB (3 parts) | 125.9 GB | Too big | Get file → | |
| BF16 | 213.8 GB (5 parts) | 215.8 GB | Too big | Get file → |
For 8 GB VRAM use Q4_0 (≈63 GB memory at 8 k context). With 16 GB VRAM Q4_K_S (≈67 GB) or Q4_K_M (≈73 GB) are suitable. For 32 GB VRAM, Q5_K_S (≈78 GB) or Q5_K_XL (≈82 GB) provide higher quality while staying within budget. Memory estimates are approximate.
What GPU do you need for Glm-4.6V?
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_XL (45.8 GB file, about 47.8 GB in use).
Which Glm-4.6V quant should you choose?
Q4_K_M is the usual starting point for Glm-4.6V: it balances file size and quality well. Here it is a 70.6 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 TQ1_0 at 36.8 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Glm-4.6V
How much VRAM does Glm-4.6V need?
About 72.6 GB at Q4_K_M with an 8K context window. That is the 70.6 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-4.6V on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 38.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Glm-4.6V GGUF?
It depends on the quant: TQ1_0 is 36.8 GB, IQ1_S is 37.0 GB, IQ1_M is 38.6 GB, IQ2_XXS is 41.2 GB, IQ2_M is 42.9 GB, Q2_K is 43.9 GB and 21 more.
What context length does Glm-4.6V 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-4.6V GGUF?
The files are on Hugging Face in the unsloth/GLM-4.6V-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-4.6V 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‑4.6V on 8 GB VRAM?
Only the lowest‑bit quants such as Q4_0 or Q4_K_S can fit, requiring around 63–67 GB of VRAM at 8 k context, which exceeds 8 GB. Thus it is not feasible on 8 GB VRAM.
Does GLM‑4.6V support vision?
Yes, the model has native vision capabilities and can process images directly.