GLM 4.7 Flash 49B needs about 30.7 GB of memory at Q4_K_M (a 28.9 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.1 GB to 39.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.3 GB.
GLM 4.7 Flash 49B – 47.7B parameter LLM with deepseek2 architecture
GLM 4.7 Flash 49B is a 47.7B parameter model built on the deepseek2 architecture. It supports reasoning and tool usage. The model is available in multiple GGUF quantizations ranging from 0.12 GB to 39.23 GB.
Good at
- Reasoning
- Tool usage
- Large context support
Limits
- No vision capability
- License not specified
- Large memory requirement for high‑quality quants
Best for
- Complex reasoning tasks
- Tool‑enabled workflows
- Research prototyping
Who it’s for. Developers and researchers who need a large‑parameter model for advanced reasoning and tool integration. The model is suitable for environments where GPU memory can accommodate the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 2.0 GB | Fits | Get file → | |
| IQ1_S | 9.8 GB | 11.6 GB | Too big | Get file → | |
| IQ1_M | 10.8 GB | 12.7 GB | Too big | Get file → | |
| IQ2_XXS | 12.6 GB | 14.5 GB | Too big | Get file → | |
| IQ2_XS | 14.1 GB | 15.9 GB | Too big | Get file → | |
| IQ2_S | 14.3 GB | 16.1 GB | Too big | Get file → | |
| IQ2_M | 15.7 GB | 17.5 GB | Too big | Get file → | |
| Q2_K_S | 16.3 GB | 18.1 GB | Too big | Get file → | |
| Q2_K | 17.5 GB | 19.4 GB | Too big | Get file → | |
| IQ3_XXS | 18.5 GB | 20.3 GB | Too big | Get file → | |
| IQ3_XS | 19.6 GB | 21.5 GB | Too big | Get file → | |
| IQ3_S | 20.7 GB | 22.5 GB | Too big | Get file → | |
| Q3_K_S | 20.7 GB | 22.5 GB | Too big | Get file → | |
| IQ3_M | 21.0 GB | 22.9 GB | Too big | Get file → | |
| Q3_K_M | 22.9 GB | 24.7 GB | Too big | Get file → | |
| Q3_K_L | 24.8 GB | 26.6 GB | Too big | Get file → | |
| IQ4_XS | 25.5 GB | 27.3 GB | Too big | Get file → | |
| Q4_0 | 27.1 GB | 28.9 GB | Too big | Get file → | |
| Q4_K_S | 27.2 GB | 29.0 GB | Too big | Get file → | |
| Q4_K_M | 28.9 GB | 30.7 GB | Too big | Get file → | |
| Q4_1 | 29.9 GB | 31.8 GB | Too big | Get file → | |
| Q5_K_S | 32.9 GB | 34.7 GB | Too big | Get file → | |
| Q5_K_M | 33.9 GB | 35.7 GB | Too big | Get file → | |
| Q6_K | 39.2 GB | 41.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (9.78 GB) or IQ1_M (10.85 GB). For 16 GB VRAM, IQ2_S (14.28 GB) or Q2_K (17.52 GB) are suitable. Higher‑quality quants such as Q4_K_M (28.9 GB) require 32 GB or more VRAM.
What GPU do you need for GLM 4.7 Flash 49B?
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 (0.1 GB file, about 2.0 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.0 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.0 GB in use).
- 12 GB VRAM: the best quant that fits is IQ1_S (9.8 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_XS (14.1 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is IQ3_M (21.0 GB file, about 22.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_1 (29.9 GB file, about 31.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (39.2 GB file, about 41.1 GB in use).
Which GLM 4.7 Flash 49B quant should you choose?
Q4_K_M is the usual starting point for GLM 4.7 Flash 49B: it balances file size and quality well. Here it is a 28.9 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 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 4.7 Flash 49B
How much VRAM does GLM 4.7 Flash 49B need?
About 30.7 GB at Q4_K_M with an 8K context window. That is the 28.9 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 4.7 Flash 49B on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GLM 4.7 Flash 49B GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 9.8 GB, IQ1_M is 10.8 GB, IQ2_XXS is 12.6 GB, IQ2_XS is 14.1 GB, IQ2_S is 14.3 GB and 18 more.
What context length does GLM 4.7 Flash 49B support?
The GGUF header lists a trained context length of 202,752 tokens (198K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.3 GB at 32K.
Where can I download GLM 4.7 Flash 49B GGUF?
The files are on Hugging Face in the mradermacher/GLM-4.7-Flash-49B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run GLM 4.7 Flash 49B on 8 GB VRAM?
Use the IQ1_S or IQ1_M quant, which require 9.78 GB and 10.85 GB respectively, slightly above 8 GB but may work with memory optimizations.
Does the model support vision tasks?
No, the model does not include vision capability.
What is the context length of the model?
The trained context length is 202752 tokens.