GL

GLM Steam 106B A12B v1

GLMGGUF by bartowskiUpdated 2025-08-28
Download on Hugging Face
Parameters110B
Context128K
Layers47
Architectureglm4moe
Smallest quant0.2 GB
Quick answer

GLM Steam 106B A12B v1 needs about 75.6 GB of memory at Q4_K_M (a 73.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 25 quants, from 0.2 GB to 117.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.

GLM Steam 106B A12B v1 – 110B parameter model with 12B active experts

GLM Steam 106B A12B v1 is a 110B parameter model with 12B active parameters in its mixture of experts. It supports up to 131072 context tokens and is optimized for reasoning and tool usage. The model is available in multiple GGUF quantizations.

Good at

  • Reasoning
  • Tool usage
  • Long‑context handling

Limits

  • No vision support
  • Large VRAM requirement for higher quantizations
  • License not specified

Best for

  • Complex reasoning tasks
  • Tool‑integrated workflows
  • Extended context conversations

Who it’s for. Developers and researchers who need a large‑scale language model with expert mixture capabilities. The model is suitable for applications requiring deep reasoning and tool integration.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 2.3 GB
Fits Get file →
IQ1_M37.9 GB 39.9 GB
Too big Get file →
IQ2_XXS39.6 GB 41.7 GB
Too big Get file →
IQ2_XS42.2 GB 44.3 GB
Too big Get file →
IQ2_S42.5 GB 44.6 GB
Too big Get file →
IQ2_M45.1 GB 47.2 GB
Too big Get file →
Q2_K46.1 GB 48.2 GB
Too big Get file →
Q2_K_L46.7 GB 48.8 GB
Too big Get file →
IQ3_XXS50.1 GB (2 parts) 52.2 GB
Too big Get file →
IQ3_XS50.8 GB (2 parts) 52.9 GB
Too big Get file →
Q3_K_S53.4 GB (2 parts) 55.5 GB
Too big Get file →
IQ3_M55.5 GB (2 parts) 57.6 GB
Too big Get file →
Q3_K_M55.5 GB (2 parts) 57.6 GB
Too big Get file →
Q3_K_L55.9 GB (2 parts) 58.0 GB
Too big Get file →
Q3_K_XL56.5 GB (2 parts) 58.5 GB
Too big Get file →
IQ4_XS60.8 GB (2 parts) 62.9 GB
Too big Get file →
IQ4_NL63.1 GB (2 parts) 65.1 GB
Too big Get file →
Q4_063.8 GB (2 parts) 65.8 GB
Too big Get file →
Q4_K_S68.3 GB (2 parts) 70.4 GB
Too big Get file →
Q4_169.5 GB (2 parts) 71.6 GB
Too big Get file →
Q4_K_M73.5 GB (2 parts) 75.6 GB
Too big Get file →
Q5_K_S78.6 GB (2 parts) 80.6 GB
Too big Get file →
Q5_K_M83.7 GB (3 parts) 85.8 GB
Too big Get file →
Q6_K99.2 GB (3 parts) 101.3 GB
Too big Get file →
Q8_0117.5 GB (3 parts) 119.5 GB
Too big Get file →

For 8‑GB VRAM, use the IQ1_M quant (file size 37.86 GB, memory 39.9 GB at 8k context). For 16‑GB VRAM, IQ2_M (45.12 GB, 47.2 GB) or Q2_K (46.1 GB, 48.2 GB) are suitable. For 32‑GB VRAM, Q3_K_M (55.48 GB, 57.6 GB) or Q4_K_M (73.5 GB, 75.6 GB) provide a balance of quality and memory usage.

What GPU do you need for GLM Steam 106B A12B v1?

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 (0.2 GB file, about 2.3 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ2_M (45.1 GB file, about 47.2 GB in use).

Which GLM Steam 106B A12B v1 quant should you choose?

Q4_K_M is the usual starting point for GLM Steam 106B A12B v1: it balances file size and quality well. Here it is a 73.5 GB file.

The Q8_0 file is 117.5 GB, about 1.6 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 0.2 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

Architectureglm4moe
Parameters110B (approximate, mixture of experts)
Active parameters12B
Layers47
Trained context131,072 tokens
KV cache (fp16)188 KB per token

Source

Quantized bybartowski
FamilyGLM
Downloads (HF)1,000
Last updated2025-08-28

Frequently asked questions about GLM Steam 106B A12B v1

How much VRAM does GLM Steam 106B A12B v1 need?

About 75.6 GB at Q4_K_M with an 8K context window. That is the 73.5 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 Steam 106B A12B v1 on an 8 GB GPU?

Yes, with the smaller files: the 0.2 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GLM Steam 106B A12B v1 GGUF?

It depends on the quant: file is 0.2 GB, IQ1_M is 37.9 GB, IQ2_XXS is 39.6 GB, IQ2_XS is 42.2 GB, IQ2_S is 42.5 GB, IQ2_M is 45.1 GB and 19 more.

What context length does GLM Steam 106B A12B v1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.3 GB at 32K.

Where can I download GLM Steam 106B A12B v1 GGUF?

The files are on Hugging Face in the bartowski/TheDrummer_GLM-Steam-106B-A12B-v1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Use the IQ1_M quant, which requires approximately 39.9 GB of VRAM at 8k context. It will not fit in 8 GB VRAM.

Does the model support vision?

No, the model does not have vision capabilities.

What is the maximum context length?

The model was trained with 131072 context tokens and can handle up to that length.

Other GGUFs of GLM-Steam-106B-A12B-v1

Similar models

Browse all →

More from bartowski

All by bartowski →

More GLM models

All GLM →

Other large models

All large models →