GL

GLM 4.7 Flash REAP 50

GLMGGUF by mradermacherUpdated 2026-08-14
Download on Hugging Face
Parameters16B
Context198K
Layers48
Architecturedeepseek2
Smallest quant0.0 GB
Quick answer

GLM 4.7 Flash REAP 50 needs about 11.1 GB of memory at Q4_K_M (a 9.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 13.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.

GLM 4.7 Flash REAP 50 – 16B MoE model optimized for code and function calling

GLM 4.7 Flash REAP 50 is a 16 billion‑parameter mixture‑of‑experts model based on the deepseek2 architecture. It is 50% expert‑pruned and trained on 202 752 context tokens. The model is released under the MIT license and supports coding, reasoning, and tools.

Good at

  • Code generation
  • Function calling
  • Agentic workflows

Limits

  • Requires 8 k context for estimates
  • Large memory footprint for higher quants
  • No vision support

Best for

  • Local code assistant
  • Tool‑integrated agents
  • Educational coding demos

Who it’s for. Developers and researchers who need a lightweight, code‑focused LLM for local inference. The model is suitable for use with llama.cpp, vLLM, and Transformers.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.4 GB
Fits Get file →
IQ1_S3.5 GB 4.8 GB
Fits Get file →
IQ1_M3.8 GB 5.2 GB
Fits Get file →
IQ2_XXS4.4 GB 5.7 GB
Fits Get file →
IQ2_XS4.8 GB 6.2 GB
Fits Get file →
IQ2_S5.0 GB 6.3 GB
Fits Get file →
IQ2_M5.4 GB 6.8 GB
Fits Get file →
Q2_K_S5.6 GB 6.9 GB
Fits Get file →
Q2_K6.0 GB 7.4 GB
Tight Get file →
IQ3_XXS6.3 GB 7.7 GB
Tight Get file →
IQ3_XS6.7 GB 8.1 GB
Too big Get file →
IQ3_S7.1 GB 8.4 GB
Too big Get file →
Q3_K_S7.1 GB 8.4 GB
Too big Get file →
IQ3_M7.2 GB 8.5 GB
Too big Get file →
Q3_K_M7.8 GB 9.1 GB
Too big Get file →
Q3_K_L8.4 GB 9.8 GB
Too big Get file →
IQ4_XS8.6 GB 10.0 GB
Too big Get file →
IQ4_NL9.1 GB 10.5 GB
Too big Get file →
Q4_09.2 GB 10.5 GB
Too big Get file →
Q4_K_S9.2 GB 10.6 GB
Too big Get file →
Q4_K_M9.7 GB 11.1 GB
Too big Get file →
Q4_110.1 GB 11.5 GB
Too big Get file →
Q5_K_S11.1 GB 12.5 GB
Too big Get file →
Q5_K_M11.4 GB 12.8 GB
Too big Get file →
Q6_K13.2 GB 14.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (4.8 GB memory) or IQ1_M (5.2 GB). If 12 GB VRAM is available, Q4_K_M (11.1 GB) is a good balance. Higher quants like Q5_K_M or Q6_K exceed typical consumer GPUs.

What GPU do you need for GLM 4.7 Flash REAP 50?

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 IQ2_XXS (4.4 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_XXS (6.3 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (10.1 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (13.2 GB file, about 14.6 GB in use).

Which GLM 4.7 Flash REAP 50 quant should you choose?

Q4_K_M is the usual starting point for GLM 4.7 Flash REAP 50: it balances file size and quality well. Here it is a 9.7 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

Architecturedeepseek2
Parameters16B (approximate, mixture of experts)
Layers48
Trained context202,752 tokens
KV cache (fp16)102 KB per token

Source

Quantized bymradermacher
FamilyGLM
Licensemit
Downloads (HF)565
Last updated2026-08-14

Frequently asked questions about GLM 4.7 Flash REAP 50

How much VRAM does GLM 4.7 Flash REAP 50 need?

About 11.1 GB at Q4_K_M with an 8K context window. That is the 9.7 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 4.7 Flash REAP 50 on an 8 GB GPU?

Yes, with IQ3_XXS: the 6.3 GB file needs about 7.7 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 50 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.5 GB, IQ1_M is 3.8 GB, IQ2_XXS is 4.4 GB, IQ2_XS is 4.8 GB, IQ2_S is 5.0 GB and 19 more.

What context length does GLM 4.7 Flash REAP 50 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 50 GGUF?

The files are on Hugging Face in the mradermacher/GLM-4.7-Flash-REAP-50-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 50 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 4.7 Flash REAP 50 on 8 GB VRAM?

Yes, with the IQ1_S or IQ1_M quant, which estimate 4.8 GB or 5.2 GB memory at 8 k context.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What is the recommended quant for 12 GB VRAM?

Use Q4_K_M, which estimates 11.1 GB memory at 8 k context.

Other GGUFs of GLM-4.7-Flash-REAP-50

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More GLM models

All GLM →

Other medium models

All medium models →