MI

Midnight-Rose-70B-v2.0.3

MidnightGGUF by backyardaiUpdated 2024-05-22
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant14.5 GB
Quick answer

Midnight-Rose-70B-v2.0.3 needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 22 quants, from 14.5 GB (IQ1_S) to 138.0 GB (F16).

Uncensored Llama2 70B model for roleplaying and storytelling

Midnight-Rose-70B-v2.0.3 is a 69‑billion‑parameter Llama2 model. It was created by backyardai and is based on Midnight Rose 70B v2.0.3. The model is designed for roleplaying and storytelling and performs well at other tasks.

Good at

  • Roleplaying
  • Storytelling
  • Prompt‑driven tasks

Limits

  • No vision support
  • Requires 4096 token context
  • Uncensored content

Best for

  • Interactive fiction
  • Character dialogue
  • Creative writing

Who it’s for. Developers and hobbyists who want a large, uncensored Llama2 model for local use. The model is suitable for users who prefer a local, GPU‑friendly implementation via llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S14.5 GB 16.4 GB
Too big Get file →
IQ2_XXS18.3 GB 20.1 GB
Too big Get file →
IQ2_XS20.3 GB 22.2 GB
Too big Get file →
IQ2_S21.4 GB 23.2 GB
Too big Get file →
IQ2_M23.2 GB 25.1 GB
Too big Get file →
Q2_K_S23.6 GB 25.4 GB
Too big Get file →
Q2_K25.5 GB 27.3 GB
Too big Get file →
IQ3_XXS26.6 GB 28.4 GB
Too big Get file →
IQ3_XS28.3 GB 30.2 GB
Too big Get file →
IQ3_S29.9 GB 31.8 GB
Too big Get file →
Q3_K_S29.9 GB 31.8 GB
Too big Get file →
IQ3_M30.9 GB 32.8 GB
Too big Get file →
Q3_K_M33.3 GB 35.1 GB
Too big Get file →
Q3_K_L36.1 GB 38.0 GB
Too big Get file →
IQ4_XS36.8 GB 38.7 GB
Too big Get file →
Q4_K_S39.2 GB 41.1 GB
Too big Get file →
Q4_K_M41.4 GB 43.3 GB
Too big Get file →
Q5_K_S47.5 GB 49.3 GB
Too big Get file →
Q5_K_M48.8 GB 50.6 GB
Too big Get file →
Q6_K56.6 GB (2 parts) 58.4 GB
Too big Get file →
Q8_073.3 GB (2 parts) 75.1 GB
Too big Get file →
F16138.0 GB (3 parts) 139.8 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (18.29 GB file, 21.5 GB memory). For 16 GB VRAM, IQ3_S (29.92 GB file, 33.1 GB memory) is a good balance. For 24 GB VRAM, Q4_K_M (41.42 GB file, 44.6 GB memory) offers higher quality.

What GPU do you need for Midnight-Rose-70B-v2.0.3?

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: the best quant that fits is IQ2_XS (20.3 GB file, about 23.5 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XS (28.3 GB file, about 31.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which Midnight-Rose-70B-v2.0.3 quant should you choose?

Q4_K_M is the usual starting point for Midnight-Rose-70B-v2.0.3: it balances file size and quality well. Here it is a 41.4 GB file.

The Q8_0 file is 73.3 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ1_S at 14.5 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
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized bybackyardai
FamilyMidnight
Licensellama2
Downloads (HF)2,403
Last updated2024-05-22

Frequently asked questions about Midnight-Rose-70B-v2.0.3

How much VRAM does Midnight-Rose-70B-v2.0.3 need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 Midnight-Rose-70B-v2.0.3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Midnight-Rose-70B-v2.0.3 GGUF?

It depends on the quant: IQ1_S is 14.5 GB, IQ2_XXS is 18.3 GB, IQ2_XS is 20.3 GB, IQ2_S is 21.4 GB, IQ2_M is 23.2 GB, Q2_K_S is 23.6 GB and 16 more.

What context length does Midnight-Rose-70B-v2.0.3 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download Midnight-Rose-70B-v2.0.3 GGUF?

The files are on Hugging Face in the backyardai/Midnight-Rose-70B-v2.0.3-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 Midnight-Rose-70B-v2.0.3 use?

Hugging Face lists the license as llama2. 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 Midnight Rose 70B v2.0.3 on 8 GB VRAM?

Use the IQ2_XXS quantization; it requires about 21.5 GB memory at 8 k context, so 8 GB VRAM is insufficient without further splitting.

Does this model support vision?

No, the model has no vision capability.

Is the model censored?

The model is uncensored; users are responsible for its use.

Other GGUFs of Midnight-Rose-70B-v2.0.3

Similar models

Browse all →

More from backyardai

All by backyardai →

More Midnight models

All Midnight →

Other large models

All large models →