ZE

MD Zephyria 42b i1

ZephyriaGGUF by mradermacherUpdated 2025-03-03
Download on Hugging Face
Parameters42B
Context128K
Layers107
Architecturellama
Smallest quant9.0 GB
Quick answer

MD Zephyria 42b i1 needs about 29.3 GB of memory at Q4_K_M (a 25.2 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 21 quants, from 9.0 GB (IQ1_S) to 34.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 14.4 GB.

MD Zephyria 42b i1 – 42‑billion parameter Llama model

MD Zephyria 42b i1 is a 42‑billion parameter Llama model with a 131072 token context window. It is a quantized version of the Zephyria family, released by mradermacher. The model is available in multiple GGUF quantizations.

Good at

  • Large context reasoning
  • Balanced low‑ and high‑level processing
  • General‑purpose text generation

Limits

  • No vision support
  • License not specified
  • Requires significant VRAM for larger quants

Best for

  • Chatbots needing long context
  • Content drafting with extended prompts
  • Research prototyping

Who it’s for. Developers and researchers who need a large‑parameter Llama model with a 131072 token context. The model is suitable for applications that can handle the memory demands of the larger quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S9.0 GB 13.1 GB
Too big Get file →
IQ1_M9.9 GB 14.0 GB
Too big Get file →
IQ2_XXS11.3 GB 15.4 GB
Too big Get file →
IQ2_XS12.5 GB 16.6 GB
Too big Get file →
IQ2_S13.2 GB 17.3 GB
Too big Get file →
IQ2_M14.3 GB 18.4 GB
Too big Get file →
Q2_K15.6 GB 19.7 GB
Too big Get file →
IQ3_XXS16.2 GB 20.3 GB
Too big Get file →
IQ3_XS17.3 GB 21.4 GB
Too big Get file →
Q3_K_S18.2 GB 22.3 GB
Too big Get file →
IQ3_S18.3 GB 22.4 GB
Too big Get file →
IQ3_M19.0 GB 23.1 GB
Too big Get file →
Q3_K_M20.3 GB 24.4 GB
Too big Get file →
Q3_K_L22.2 GB 26.3 GB
Too big Get file →
IQ4_XS22.6 GB 26.6 GB
Too big Get file →
Q4_023.8 GB 27.9 GB
Too big Get file →
Q4_K_S23.9 GB 28.0 GB
Too big Get file →
Q4_K_M25.2 GB 29.3 GB
Too big Get file →
Q5_K_S29.0 GB 33.1 GB
Too big Get file →
Q5_K_M29.8 GB 33.8 GB
Too big Get file →
Q6_K34.6 GB 38.7 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (9.04 GB, 13.1 GB memory at 8 k context) or IQ1_M (9.87 GB, 14 GB). For 16 GB VRAM, IQ2_S (13.23 GB, 17.3 GB) or Q2_K (15.59 GB, 19.7 GB) are suitable. For 24 GB VRAM, Q4_K_M (25.22 GB, 29.3 GB) or Q5_K_S (29 GB, 33.1 GB) provide higher quality.

What GPU do you need for MD Zephyria 42b i1?

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: the best quant that fits is IQ2_XXS (11.3 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ3_M (19.0 GB file, about 23.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (25.2 GB file, about 29.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (34.6 GB file, about 38.7 GB in use).

Which MD Zephyria 42b i1 quant should you choose?

Q4_K_M is the usual starting point for MD Zephyria 42b i1: it balances file size and quality well. Here it is a 25.2 GB file.

If memory is tight, the smallest file is IQ1_S at 9.0 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

Architecturellama
Parameters42B
Layers107
Trained context131,072 tokens
KV cache (fp16)428 KB per token

Source

Quantized bymradermacher
FamilyZephyria
Downloads (HF)1,443
Last updated2025-03-03

Frequently asked questions about MD Zephyria 42b i1

How much VRAM does MD Zephyria 42b i1 need?

About 29.3 GB at Q4_K_M with an 8K context window. That is the 25.2 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 MD Zephyria 42b i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MD Zephyria 42b i1 GGUF?

It depends on the quant: IQ1_S is 9.0 GB, IQ1_M is 9.9 GB, IQ2_XXS is 11.3 GB, IQ2_XS is 12.5 GB, IQ2_S is 13.2 GB, IQ2_M is 14.3 GB and 15 more.

What context length does MD Zephyria 42b i1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.6 GB at 8K and 14.4 GB at 32K.

Where can I download MD Zephyria 42b i1 GGUF?

The files are on Hugging Face in the mradermacher/MD-Zephyria-42b-i1-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 MD Zephyria 42b i1 on 8 GB VRAM?

Use the IQ1_S or IQ1_M quant, which fit within 8 GB VRAM and require about 13–14 GB memory at 8 k context.

What is the context length of this model?

The model supports a context length of 131072 tokens.

Does the model support vision tasks?

No, the model does not have vision capabilities.

Other GGUFs of MD-Zephyria-42b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Zephyria models

All Zephyria →

Other large models

All large models →