GL

GLM 4.7 Flash Heretic

GLMGGUF by bartowskiUpdated 2026-03-04
Download on Hugging Face
Parameters29.9B
Context198K
Layers47
Architecturedeepseek2
Smallest quant0.1 GB
Quick answer

GLM 4.7 Flash Heretic needs about 19.9 GB of memory at Q4_K_M (a 18.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 28 quants, from 0.1 GB to 59.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.

GLM 4.7 Flash Heretic – a 29.9 B‑parameter MoE model for local inference

GLM 4.7 Flash Heretic is a 29.9 B‑parameter deepseek2 architecture model. It is a mixture of experts and supports inference via llama.cpp, vLLM, and SGLang. The model is released under the MIT license and is available in multiple quantizations.

Good at

  • Large‑context reasoning
  • Efficient inference on GPUs
  • Flexible quantization options

Limits

  • Requires 8 k context for memory estimates
  • No vision support
  • Mixture of experts may increase latency

Best for

  • Local chatbot deployment
  • Research prototyping
  • Embedded inference on edge devices

Who it’s for. Engineers and researchers who need a high‑capacity language model that can be run locally with llama.cpp or similar frameworks. The model is suitable for those who can manage the memory requirements of the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.4 GB
Fits Get file →
IQ2_XXS8.5 GB 9.9 GB
Too big Get file →
IQ2_XS9.4 GB 10.7 GB
Too big Get file →
IQ2_S9.6 GB 11.0 GB
Too big Get file →
IQ2_M10.5 GB 11.9 GB
Too big Get file →
Q2_K11.1 GB 12.4 GB
Too big Get file →
Q2_K_L11.4 GB 12.8 GB
Too big Get file →
IQ3_XXS13.0 GB 14.3 GB
Too big Get file →
IQ3_XS13.4 GB 14.7 GB
Too big Get file →
Q3_K_S13.5 GB 14.9 GB
Too big Get file →
Q3_K_M14.1 GB 15.5 GB
Too big Get file →
Q3_K_L14.5 GB 15.8 GB
Too big Get file →
IQ3_M14.6 GB 15.9 GB
Too big Get file →
Q3_K_XL14.8 GB 16.1 GB
Too big Get file →
IQ4_XS16.3 GB 17.7 GB
Too big Get file →
IQ4_NL17.2 GB 18.6 GB
Too big Get file →
Q4_017.4 GB 18.7 GB
Too big Get file →
Q4_K_S17.8 GB 19.2 GB
Too big Get file →
Q4_K_M18.5 GB 19.9 GB
Too big Get file →
Q4_K_L18.8 GB 20.1 GB
Too big Get file →
Q4_119.0 GB 20.3 GB
Too big Get file →
Q5_K_S20.9 GB 22.3 GB
Too big Get file →
Q5_K_M21.6 GB 23.0 GB
Too big Get file →
Q5_K_L21.8 GB 23.2 GB
Too big Get file →
Q6_K25.9 GB 27.2 GB
Too big Get file →
Q6_K_L26.1 GB 27.4 GB
Too big Get file →
Q8_031.8 GB 33.2 GB
Too big Get file →
BF1659.9 GB (2 parts) 61.2 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (file size 8.54 GB, memory 9.9 GB) or IQ2_XS (9.41 GB, 10.7 GB). For 16 GB VRAM, IQ4_XS (16.32 GB, 17.7 GB) or Q4_K_M (18.54 GB, 19.9 GB) are suitable. For 32 GB VRAM, Q6_K (25.9 GB, 27.2 GB) or Q8_0 (31.84 GB, 33.2 GB) provide higher quality.

What GPU do you need for GLM 4.7 Flash Heretic?

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_M (10.5 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_M (14.6 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_L (21.8 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_L (26.1 GB file, about 27.4 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 Heretic quant should you choose?

Q4_K_M is the usual starting point for GLM 4.7 Flash Heretic: it balances file size and quality well. Here it is a 18.5 GB file.

The Q8_0 file is 31.8 GB, about 1.7 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
Parameters29.9B (approximate, mixture of experts)
Layers47
Trained context202,752 tokens
KV cache (fp16)100 KB per token

Source

Quantized bybartowski
FamilyGLM
Licensemit
Downloads (HF)1,461
Last updated2026-03-04

Frequently asked questions about GLM 4.7 Flash Heretic

How much VRAM does GLM 4.7 Flash Heretic need?

About 19.9 GB at Q4_K_M with an 8K context window. That is the 18.5 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 Heretic 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 Heretic GGUF?

It depends on the quant: file is 0.1 GB, IQ2_XXS is 8.5 GB, IQ2_XS is 9.4 GB, IQ2_S is 9.6 GB, IQ2_M is 10.5 GB, Q2_K is 11.1 GB and 22 more.

What context length does GLM 4.7 Flash Heretic support?

The GGUF header lists a trained context length of 202,752 tokens (198K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.4 GB at 32K.

Where can I download GLM 4.7 Flash Heretic GGUF?

The files are on Hugging Face in the bartowski/jtl11_GLM-4.7-Flash-heretic-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 Heretic 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 Heretic on 8 GB VRAM?

Use IQ2_XXS or IQ2_XS quantizations; they estimate 9.9 GB and 10.7 GB memory at 8 k context, which may fit with VRAM overhead.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the MIT license.

Similar models

Browse all →

More from bartowski

All by bartowski →

More GLM models

All GLM →

Other medium models

All medium models →