GLM 4.7 Flash REAP 39 needs about 12.9 GB of memory at Q4_K_M (a 11.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 0.0 GB to 15.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.
GLM 4.7 Flash REAP 39 – 19.1B parameter model optimized for code and function calling
GLM 4.7 Flash REAP 39 is a 19.1B parameter model from the GLM family, built on the deepseek2 architecture. It is 50% expert‑pruned using REAP and is calibrated for coding, function calling, and agentic workflows. The model is released under the MIT license.
Good at
- Code generation
- Function calling
- Agentic task support
Limits
- Requires 202752 context tokens
- No vision support
- GGUF files pending re‑upload by January 24, 2026
Best for
- Local code generation with llama.cpp
- Tool‑calling workflows
- Agentic task prototyping
Who it’s for. Developers needing a locally deployable code‑focused LLM with function‑calling capability. Researchers testing expert‑pruned models on local inference setups.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.4 GB | Fits | Get file → | |
| IQ1_S | 4.1 GB | 5.4 GB | Fits | Get file → | |
| IQ1_M | 4.5 GB | 5.8 GB | Fits | Get file → | |
| IQ2_XXS | 5.2 GB | 6.5 GB | Fits | Get file → | |
| IQ2_XS | 5.7 GB | 7.1 GB | Fits | Get file → | |
| IQ2_S | 5.9 GB | 7.2 GB | Tight | Get file → | |
| IQ2_M | 6.4 GB | 7.8 GB | Tight | Get file → | |
| Q2_K_S | 6.6 GB | 8.0 GB | Tight | Get file → | |
| Q2_K | 7.1 GB | 8.5 GB | Too big | Get file → | |
| IQ3_XXS | 7.5 GB | 8.8 GB | Too big | Get file → | |
| IQ3_XS | 7.9 GB | 9.3 GB | Too big | Get file → | |
| IQ3_S | 8.4 GB | 9.7 GB | Too big | Get file → | |
| Q3_K_S | 8.4 GB | 9.7 GB | Too big | Get file → | |
| IQ3_M | 8.5 GB | 9.9 GB | Too big | Get file → | |
| Q3_K_M | 9.2 GB | 10.6 GB | Too big | Get file → | |
| Q3_K_L | 10.0 GB | 11.3 GB | Too big | Get file → | |
| IQ4_XS | 10.3 GB | 11.6 GB | Too big | Get file → | |
| Q4_0 | 10.9 GB | 12.2 GB | Too big | Get file → | |
| Q4_K_S | 10.9 GB | 12.3 GB | Too big | Get file → | |
| Q4_K_M | 11.6 GB | 12.9 GB | Too big | Get file → | |
| Q4_1 | 12.0 GB | 13.4 GB | Too big | Get file → | |
| Q5_K_S | 13.2 GB | 14.5 GB | Too big | Get file → | |
| Q5_K_M | 13.6 GB | 14.9 GB | Too big | Get file → | |
| Q6_K | 15.7 GB | 17.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (4.07 GB, 5.4 GB memory) or Q2_K_S (6.62 GB, 8 GB memory). For 12 GB VRAM, Q4_K_M (11.57 GB, 12.9 GB memory) is suitable. Higher‑quality quants like Q5_K_M (13.56 GB, 14.9 GB memory) require 16 GB+ VRAM.
What GPU do you need for GLM 4.7 Flash REAP 39?
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 IQ1_M (4.5 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K_S (6.6 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is IQ4_XS (10.3 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (13.6 GB file, about 14.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (15.7 GB file, about 17.1 GB in use).
Which GLM 4.7 Flash REAP 39 quant should you choose?
Q4_K_M is the usual starting point for GLM 4.7 Flash REAP 39: it balances file size and quality well. Here it is a 11.6 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 4.7 Flash REAP 39
How much VRAM does GLM 4.7 Flash REAP 39 need?
About 12.9 GB at Q4_K_M with an 8K context window. That is the 11.6 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 4.7 Flash REAP 39 on an 8 GB GPU?
Yes, with Q2_K_S: the 6.6 GB file needs about 8.0 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 REAP 39 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 4.1 GB, IQ1_M is 4.5 GB, IQ2_XXS is 5.2 GB, IQ2_XS is 5.7 GB, IQ2_S is 5.9 GB and 18 more.
What context length does GLM 4.7 Flash REAP 39 support?
The GGUF header lists a trained context length of 202,752 tokens (198K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.4 GB at 32K.
Where can I download GLM 4.7 Flash REAP 39 GGUF?
The files are on Hugging Face in the mradermacher/GLM-4.7-Flash-REAP-39-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 4.7 Flash REAP 39 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 IQ1_S or Q2_K_S quant, which estimate 5.4 GB or 8 GB memory at 8 k context.
Is the GGUF file ready for llama.cpp?
GGUF files are scheduled for re‑upload by January 24, 2026; current files may have compatibility issues.
What license does the model use?
The model is released under the MIT license.