DA

MN DARKEST Universe Infinity Claude High Reasoning 29B

DarkestGGUF by mradermacherUpdated 2026-01-23
Download on Hugging Face
Parameters29.2B
Context1000K
Layers102
Architecturellama
Smallest quant0.0 GB
Quick answer

MN DARKEST Universe Infinity Claude High Reasoning 29B needs about 21.5 GB of memory at Q4_K_M (a 17.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 23.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 13.7 GB.

29B Llama model focused on reasoning and roleplay

MN DARKEST Universe Infinity Claude High Reasoning 29B is a 29.2‑billion parameter Llama architecture model. It supports reasoning, roleplay, and tool usage. The model is released under the apache‑2.0 license.

Good at

  • Advanced reasoning
  • Roleplay scenarios
  • Tool integration

Limits

  • Large context size of 1,024,000 tokens
  • Requires high VRAM for full precision
  • No vision capability

Best for

  • Complex problem solving
  • Interactive storytelling
  • Automated tool workflows

Who it’s for. Developers and researchers needing a large reasoning‑capable Llama model. The model is suitable for applications that can accommodate its memory demands and do not require vision or multimodal input.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.9 GB
Fits Get file →
IQ1_S6.6 GB 10.5 GB
Too big Get file →
IQ1_M7.1 GB 11.1 GB
Too big Get file →
IQ2_XXS8.1 GB 12.0 GB
Too big Get file →
IQ2_XS8.9 GB 12.8 GB
Too big Get file →
IQ2_S9.4 GB 13.3 GB
Too big Get file →
IQ2_M10.1 GB 14.1 GB
Too big Get file →
Q2_K_S10.2 GB 14.2 GB
Too big Get file →
Q2_K11.0 GB 14.9 GB
Too big Get file →
IQ3_XXS11.4 GB 15.4 GB
Too big Get file →
IQ3_XS12.2 GB 16.1 GB
Too big Get file →
Q3_K_S12.8 GB 16.7 GB
Too big Get file →
IQ3_S12.9 GB 16.8 GB
Too big Get file →
IQ3_M13.3 GB 17.2 GB
Too big Get file →
Q3_K_M14.2 GB 18.1 GB
Too big Get file →
Q3_K_L15.4 GB 19.3 GB
Too big Get file →
IQ4_XS15.8 GB 19.7 GB
Too big Get file →
Q4_016.6 GB 20.6 GB
Too big Get file →
Q4_K_S16.7 GB 20.6 GB
Too big Get file →
Q4_K_M17.6 GB 21.5 GB
Too big Get file →
Q4_118.4 GB 22.3 GB
Too big Get file →
Q5_K_S20.1 GB 24.1 GB
Too big Get file →
Q5_K_M20.7 GB 24.6 GB
Too big Get file →
Q6_K23.9 GB 27.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (6.57 GB, 10.5 GB memory at 8 k context). With 12 GB VRAM, IQ2_XS (8.91 GB, 12.8 GB memory) is a good balance. For 16 GB VRAM, Q4_K_M (17.6 GB, 21.5 GB memory) offers higher quality while staying within limits.

What GPU do you need for MN DARKEST Universe Infinity Claude High Reasoning 29B?

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 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.9 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.9 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_XXS (8.1 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (11.4 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (18.4 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (23.9 GB file, about 27.8 GB in use).

Which MN DARKEST Universe Infinity Claude High Reasoning 29B quant should you choose?

Q4_K_M is the usual starting point for MN DARKEST Universe Infinity Claude High Reasoning 29B: it balances file size and quality well. Here it is a 17.6 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
Parameters29.2B
Layers102
Trained context1,024,000 tokens
KV cache (fp16)408 KB per token

Source

Quantized bymradermacher
FamilyDarkest
Licenseapache-2.0
Downloads (HF)814
Last updated2026-01-23

Frequently asked questions about MN DARKEST Universe Infinity Claude High Reasoning 29B

How much VRAM does MN DARKEST Universe Infinity Claude High Reasoning 29B need?

About 21.5 GB at Q4_K_M with an 8K context window. That is the 17.6 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 MN DARKEST Universe Infinity Claude High Reasoning 29B on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MN DARKEST Universe Infinity Claude High Reasoning 29B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 6.6 GB, IQ1_M is 7.1 GB, IQ2_XXS is 8.1 GB, IQ2_XS is 8.9 GB, IQ2_S is 9.4 GB and 18 more.

What context length does MN DARKEST Universe Infinity Claude High Reasoning 29B support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 3.4 GB at 8K and 13.7 GB at 32K.

Where can I download MN DARKEST Universe Infinity Claude High Reasoning 29B GGUF?

The files are on Hugging Face in the mradermacher/MN-DARKEST-Universe-Infinity-Claude-High-Reasoning-29B-i1-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 MN DARKEST Universe Infinity Claude High Reasoning 29B use?

Hugging Face lists the license as apache-2.0. 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 this model on 8 GB VRAM?

Use the IQ1_S quant, which is 6.57 GB and requires about 10.5 GB memory at 8 k context.

Does the model support vision?

No, the model does not have vision or multimodal capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Darkest models

All Darkest →

Other medium models

All medium models →