MI

zephyr-orpo-141b-A35b-v0.1

MistralGGUF by bartowskiUpdated 2024-04-13
Download on Hugging Face
Parameters141B
Context64K
Layers56
Architecturellama
Smallest quant52.1 GB
Quick answer

zephyr-orpo-141b-A35b-v0.1 needs about 88.0 GB of memory at Q4_K_M (a 85.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 13 quants, from 52.1 GB (Q2_K) to 100.0 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Large 141B parameter LLM with 65K context and sparse Mixture of Experts

zephyr-orpo-141b-A35b-v0.1 is a 141B parameter model based on Mixtral-8x22B. It supports a context length of 65536 tokens and is released under the Apache‑2.0 license. The model is available in multiple llama.cpp quantizations.

Good at

  • Large context handling
  • Sparse Mixture of Experts architecture
  • Apache‑2.0 licensed

Limits

  • Requires high VRAM for full precision
  • No vision capabilities
  • No moderation mechanisms

Best for

  • Long‑form text generation
  • Research prototyping
  • Large‑scale inference on powerful GPUs

Who it’s for. Engineers and researchers who need a high‑capacity language model with a very long context window and are comfortable managing large memory footprints. The model is suitable for environments that can accommodate the 141B parameter size and the associated hardware requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K52.1 GB (5 parts) 54.5 GB
Too big Get file →
IQ3_XS58.2 GB (5 parts) 60.6 GB
Too big Get file →
IQ3_S61.5 GB (5 parts) 63.9 GB
Too big Get file →
Q3_K_S61.5 GB (5 parts) 63.9 GB
Too big Get file →
IQ3_M64.5 GB (5 parts) 66.9 GB
Too big Get file →
Q3_K_M67.8 GB (5 parts) 70.2 GB
Too big Get file →
Q3_K_L72.6 GB (5 parts) 75.0 GB
Too big Get file →
IQ4_XS76.4 GB (5 parts) 78.7 GB
Too big Get file →
IQ4_NL80.5 GB (5 parts) 82.9 GB
Too big Get file →
Q4_K_S80.5 GB (5 parts) 82.9 GB
Too big Get file →
Q4_K_M85.6 GB (5 parts) 88.0 GB
Too big Get file →
Q5_K_S97.0 GB (5 parts) 99.4 GB
Too big Get file →
Q5_K_M100.0 GB (5 parts) 102.3 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 52.1 GB, memory 54.5 GB at 8 k context). For 16 GB VRAM, Q3_K_S (61.5 GB, 63.9 GB). For 24 GB VRAM, Q4_K_M (85.59 GB, 88 GB). These estimates are approximate and assume the model is loaded on GPU with the corresponding quantization.

What GPU do you need for zephyr-orpo-141b-A35b-v0.1?

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: no quant fits at an 8K context.

Which zephyr-orpo-141b-A35b-v0.1 quant should you choose?

Q4_K_M is the usual starting point for zephyr-orpo-141b-A35b-v0.1: it balances file size and quality well. Here it is a 85.6 GB file.

If memory is tight, the smallest file is Q2_K at 52.1 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
Parameters141B (approximate, mixture of experts)
Layers56
Trained context65,536 tokens
KV cache (fp16)224 KB per token

Source

Quantized bybartowski
FamilyMistral
Licenseapache-2.0
Downloads (HF)2,409
Last updated2024-04-13

Frequently asked questions about zephyr-orpo-141b-A35b-v0.1

How much VRAM does zephyr-orpo-141b-A35b-v0.1 need?

About 88.0 GB at Q4_K_M with an 8K context window. That is the 85.6 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 zephyr-orpo-141b-A35b-v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 54.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of zephyr-orpo-141b-A35b-v0.1 GGUF?

It depends on the quant: Q2_K is 52.1 GB, IQ3_XS is 58.2 GB, IQ3_S is 61.5 GB, Q3_K_S is 61.5 GB, IQ3_M is 64.5 GB, Q3_K_M is 67.8 GB and 7 more.

What context length does zephyr-orpo-141b-A35b-v0.1 support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download zephyr-orpo-141b-A35b-v0.1 GGUF?

The files are on Hugging Face in the bartowski/zephyr-orpo-141b-A35b-v0.1-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 zephyr-orpo-141b-A35b-v0.1 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 zephyr-orpo-141b-A35b-v0.1 on 8 GB VRAM?

Only with a very low‑precision quant like Q2_K, which still requires about 54.5 GB of memory at 8 k context, so it is not feasible on 8 GB VRAM.

What license does the model use?

The model is released under the Apache‑2.0 license.

Does the model support vision inputs?

No, the model does not have vision capabilities.

Other GGUFs of Mixtral-8x22B-v0.1

Similar models

Browse all →

More from bartowski

All by bartowski →

More Mistral models

All Mistral →

Other large models

All large models →