GL

GLM 4.6 gguf q2ks mixed AutoRound

GLMGGUF by INC4AIUpdated 2025-10-24
Download on Hugging Face
Parameters357B
Context198K
Layers93
Architectureglm4moe
Smallest quant136.7 GB
Quick answer

GLM 4.6 gguf q2ks mixed AutoRound needs about 140.3 GB of memory at Q2_K_S (a 136.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 12.5 GB.

GLM 4.6 gguf q2ks mixed AutoRound is a 357B-parameter GLM model in GGUF format, quantized by INC4AI. Its trained context length is 198K tokens. The repository has 1 quant file, from 136.7 GB (Q2_K_S) to 136.7 GB (Q2_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K_S136.7 GB (15 parts) 140.3 GB
Too big Get file →

What GPU do you need for GLM 4.6 gguf q2ks mixed AutoRound?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which GLM 4.6 gguf q2ks mixed AutoRound quant should you choose?

Q2_K_S (136.7 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureglm4moe
Parameters357B (approximate, mixture of experts)
Layers93
Trained context202,752 tokens
KV cache (fp16)372 KB per token

Source

Quantized byINC4AI
FamilyGLM
Base modelzai-org/GLM-4.6
Downloads (HF)12
Last updated2025-10-24

Frequently asked questions about GLM 4.6 gguf q2ks mixed AutoRound

How much VRAM does GLM 4.6 gguf q2ks mixed AutoRound need?

About 140.3 GB at Q2_K_S with an 8K context window. That is the 136.7 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 4.6 gguf q2ks mixed AutoRound on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 140.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 4.6 gguf q2ks mixed AutoRound GGUF?

It depends on the quant: Q2_K_S is 136.7 GB.

What context length does GLM 4.6 gguf q2ks mixed AutoRound support?

The GGUF header lists a trained context length of 202,752 tokens (198K). The KV cache grows with the context you use: about 3.1 GB at 8K and 12.5 GB at 32K.

Where can I download GLM 4.6 gguf q2ks mixed AutoRound GGUF?

The files are on Hugging Face in the INC4AI/GLM-4.6-gguf-q2ks-mixed-AutoRound repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of GLM-4.6

Similar models

Browse all →

More from INC4AI

All by INC4AI →

More GLM models

All GLM →

Other large models

All large models →