GL

GLM-4.7-Flash-Coder

GLMGGUF by ngquocvinhUpdated 2026-09-24
Download on Hugging Face
Parameters30B
Context198K
Layers48
Architecturedeepseek2
Smallest quant0.1 GB
Quick answer

GLM-4.7-Flash-Coder needs about 19.5 GB of memory at Q4_K_M (a 18.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 15 quants, from 0.1 GB to 31.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.

30B Mixture-of-Experts coding model with efficient tool use

GLM-4.7-Flash-Coder is a 30B Mixture-of-Experts model fine‑tuned for agentic coding tasks. It was trained with Halo on 32k real software‑engineering trajectories and supports concurrent tool calls. The model is released under the MIT license and available in multiple GGUF quantizations.

Good at

  • Agentic coding with tool calls
  • Concurrent tool usage
  • Reasoning efficiency

Limits

  • Requires 8k context for memory estimates
  • No vision support
  • Large VRAM needed for higher‑quality quants

Best for

  • Automated code debugging
  • Multi‑turn coding assistants
  • Tool‑enabled code generation

Who it’s for. Developers and researchers needing a coding‑focused LLM with efficient turn handling. The model is suitable for environments that can run GGUF files and support tool integration.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.4 GB
Fits Get file →
IQ1_M6.9 GB 8.2 GB
Too big Get file →
IQ2_XS8.9 GB 10.2 GB
Too big Get file →
Q2_K11.0 GB 12.4 GB
Too big Get file →
Q3_K_S13.0 GB 14.4 GB
Too big Get file →
IQ3_M13.2 GB 14.6 GB
Too big Get file →
Q3_K_M14.4 GB 15.8 GB
Too big Get file →
Q3_K_L15.6 GB 16.9 GB
Too big Get file →
IQ4_XS16.2 GB 17.6 GB
Too big Get file →
Q4_K_S17.1 GB 18.5 GB
Too big Get file →
Q4_K_M18.1 GB 19.5 GB
Too big Get file →
Q5_K_S20.7 GB 22.0 GB
Too big Get file →
Q5_K_M21.3 GB 22.6 GB
Too big Get file →
Q6_K24.6 GB 26.0 GB
Too big Get file →
Q8_031.8 GB 33.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_M (6.89 GB) or Q2_K (11.04 GB) as a balance of size and performance. If 12 GB VRAM is available, Q3_K_S (13.03 GB) or IQ3_M (13.24 GB) offer better fidelity. Larger VRAM allows Q4_K_M (18.13 GB) or Q5_K_M (21.26 GB) for higher quality.

What GPU do you need for GLM-4.7-Flash-Coder?

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 1.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_XS (8.9 GB file, about 10.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_M (14.4 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (21.3 GB file, about 22.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (24.6 GB file, about 26.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (31.8 GB file, about 33.2 GB in use).

Which GLM-4.7-Flash-Coder quant should you choose?

Q4_K_M is the usual starting point for GLM-4.7-Flash-Coder: it balances file size and quality well. Here it is a 18.1 GB file.

The Q8_0 file is 31.8 GB, about 1.8 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 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

Architecturedeepseek2
Parameters30B (approximate, mixture of experts)
Layers48
Trained context202,752 tokens
KV cache (fp16)102 KB per token

Source

Quantized byngquocvinh
FamilyGLM
Licensemit
Downloads (HF)3,764
Last updated2026-09-24

Frequently asked questions about GLM-4.7-Flash-Coder

How much VRAM does GLM-4.7-Flash-Coder need?

About 19.5 GB at Q4_K_M with an 8K context window. That is the 18.1 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-Coder on an 8 GB GPU?

Yes, with the smaller files: the 0.1 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-4.7-Flash-Coder GGUF?

It depends on the quant: file is 0.1 GB, IQ1_M is 6.9 GB, IQ2_XS is 8.9 GB, Q2_K is 11.0 GB, Q3_K_S is 13.0 GB, IQ3_M is 13.2 GB and 9 more.

What context length does GLM-4.7-Flash-Coder 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-Coder GGUF?

The files are on Hugging Face in the ngquocvinh/GLM-4.7-Flash-Coder-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-Coder 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-Coder on 8 GB VRAM?

Yes, the IQ1_M quant (~6.9 GB) fits within 8 GB VRAM and provides a usable trade‑off.

Does the model support vision or image input?

No, the model has no vision capabilities and is focused solely on text and tool calls.

What context length is required for full functionality?

The model was trained with a 75k‑token context, but runtime validation is limited to 8k tokens.

Other GGUFs of GLM-4.7-Flash-Coder

Similar models

Browse all →

More from ngquocvinh

All by ngquocvinh →

More GLM models

All GLM →

Other medium models

All medium models →