RO

Rolodex 12B

RolodexGGUF by mradermacherUpdated 2026-10-08
Download on Hugging Face
Parameters110B
Context128K
Layers47
Architectureglm4moe
Smallest quant45.0 GB
Quick answer

Rolodex 12B needs about 74.9 GB of memory at Q4_K_M (a 72.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 10 quants, from 45.0 GB (Q2_K) to 99.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.

Rolodex 12B is a 110B-parameter Rolodex model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 10 quant files, from 45.0 GB (Q2_K) to 99.0 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K45.0 GB 47.0 GB
Too big Get file →
Q3_K_S52.4 GB 54.4 GB
Too big Get file →
Q3_K_M57.0 GB 59.1 GB
Too big Get file →
Q3_K_L59.4 GB 61.5 GB
Too big Get file →
IQ4_XS60.6 GB 62.7 GB
Too big Get file →
Q4_K_S66.9 GB 68.9 GB
Too big Get file →
Q4_K_M72.9 GB 74.9 GB
Too big Get file →
Q5_K_S78.3 GB 80.3 GB
Too big Get file →
Q5_K_M83.4 GB 85.5 GB
Too big Get file →
Q6_K99.0 GB 101.1 GB
Too big Get file →

What GPU do you need for Rolodex 12B?

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: the best quant that fits is Q2_K (45.0 GB file, about 47.0 GB in use).

Which Rolodex 12B quant should you choose?

Q4_K_M is the usual starting point for Rolodex 12B: it balances file size and quality well. Here it is a 72.9 GB file.

If memory is tight, the smallest file is Q2_K at 45.0 GB, with the quality trade-offs that come with fewer bits. 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
Parameters110B (approximate, mixture of experts)
Layers47
Trained context131,072 tokens
KV cache (fp16)188 KB per token

Source

Quantized bymradermacher
FamilyRolodex
Licensemit
Downloads (HF)85
Last updated2026-10-08

Frequently asked questions about Rolodex 12B

How much VRAM does Rolodex 12B need?

About 74.9 GB at Q4_K_M with an 8K context window. That is the 72.9 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 Rolodex 12B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 47.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Rolodex 12B GGUF?

It depends on the quant: Q2_K is 45.0 GB, Q3_K_S is 52.4 GB, Q3_K_M is 57.0 GB, Q3_K_L is 59.4 GB, IQ4_XS is 60.6 GB, Q4_K_S is 66.9 GB and 4 more.

What context length does Rolodex 12B 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 Rolodex 12B GGUF?

The files are on Hugging Face in the mradermacher/Rolodex-12B-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 Rolodex 12B 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.

Other GGUFs of Rolodex-12B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Rolodex models

All Rolodex →

Other large models

All large models →