MA

Ne Marvin 22B

MarvinGGUF by mradermacherUpdated 2025-12-07
Download on Hugging Face
Parameters22.1B
Context128K
Layers76
Architecturellama
Smallest quant0.0 GB
Quick answer

Ne Marvin 22B needs about 16.4 GB of memory at Q4_K_M (a 13.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 15 quants, from 0.0 GB to 18.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 10.2 GB.

Ne Marvin 22B is a 22.1B-parameter Marvin model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 15 quant files, from 0.0 GB to 18.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.1 GB
Fits Get file →
IQ1_M5.5 GB 8.5 GB
Too big Get file →
IQ2_XXS6.2 GB 9.3 GB
Too big Get file →
IQ2_M7.7 GB 10.8 GB
Too big Get file →
Q2_K_S7.8 GB 10.9 GB
Too big Get file →
Q2_K8.4 GB 11.5 GB
Too big Get file →
IQ3_XXS8.7 GB 11.8 GB
Too big Get file →
Q3_K_S9.8 GB 12.8 GB
Too big Get file →
IQ3_M10.1 GB 13.2 GB
Too big Get file →
Q3_K_M10.8 GB 13.8 GB
Too big Get file →
Q3_K_L11.7 GB 14.8 GB
Too big Get file →
IQ4_XS12.0 GB 15.0 GB
Too big Get file →
Q4_K_S12.7 GB 15.7 GB
Too big Get file →
Q4_K_M13.4 GB 16.4 GB
Too big Get file →
Q6_K18.1 GB 21.2 GB
Too big Get file →

What GPU do you need for Ne Marvin 22B?

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 (0.0 GB file, about 3.1 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.1 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.1 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_XXS (8.7 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (12.7 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (18.1 GB file, about 21.2 GB in use).

Which Ne Marvin 22B quant should you choose?

Q4_K_M is the usual starting point for Ne Marvin 22B: it balances file size and quality well. Here it is a 13.4 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 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

Architecturellama
Parameters22.1B
Layers76
Trained context131,072 tokens
KV cache (fp16)304 KB per token

Source

Quantized bymradermacher
FamilyMarvin
Downloads (HF)3
Last updated2025-12-07

Frequently asked questions about Ne Marvin 22B

How much VRAM does Ne Marvin 22B need?

About 16.4 GB at Q4_K_M with an 8K context window. That is the 13.4 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 Ne Marvin 22B on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ne Marvin 22B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_M is 5.5 GB, IQ2_XXS is 6.2 GB, IQ2_M is 7.7 GB, Q2_K_S is 7.8 GB, Q2_K is 8.4 GB and 9 more.

What context length does Ne Marvin 22B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.6 GB at 8K and 10.2 GB at 32K.

Where can I download Ne Marvin 22B GGUF?

The files are on Hugging Face in the mradermacher/Ne-Marvin-22B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Ne-Marvin-22B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Marvin models

All Marvin →

Other medium models

All medium models →