AI

airoboros-65b-gpt4-m2.0

AiroborosGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters65B
Context2K
Layers80
Architecturellama
Smallest quant14.2 GB
Quick answer

airoboros-65b-gpt4-m2.0 needs about 61.3 GB of memory at Q4_K_M (a 39.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 20 quants, from 14.2 GB (IQ1_S) to 46.2 GB (Q5_K_M).

A 65B instruction‑fine‑tuned Llama‑2 model with GPT‑4‑derived prompts

airoboros‑65b‑gpt4‑m2.0 is a 65B‑parameter Llama‑2 model fine‑tuned on synthetic GPT‑4 instructions. It uses a 2048‑token context window and is released under a CC‑BY‑NC‑4.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Instruction following
  • Long‑form dialogue
  • Complex reasoning

Limits

  • No vision support
  • CC‑BY‑NC‑4.0 license restricts commercial use
  • Requires large VRAM for full precision

Best for

  • Chatbot development
  • Research prototyping
  • Educational demos

Who it’s for. Developers and researchers needing a large instruction‑tuned Llama‑2 model. The model is suitable for non‑commercial projects due to its license. It is ideal for users with access to high‑end GPUs or sufficient RAM for the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S14.2 GB 20.1 GB
Too big Get file →
IQ1_M15.4 GB 21.3 GB
Too big Get file →
IQ2_XXS17.5 GB 23.3 GB
Too big Get file →
IQ2_XS19.3 GB 25.1 GB
Too big Get file →
IQ2_S20.8 GB 26.7 GB
Too big Get file →
IQ2_M22.4 GB 28.3 GB
Too big Get file →
Q2_K24.1 GB 30.0 GB
Too big Get file →
IQ3_XXS24.7 GB 30.5 GB
Too big Get file →
IQ3_XS26.6 GB 32.5 GB
Too big Get file →
IQ3_S28.2 GB 34.0 GB
Too big Get file →
Q3_K_S28.2 GB 34.0 GB
Too big Get file →
IQ3_M29.8 GB 35.7 GB
Too big Get file →
Q3_K_M31.6 GB 37.5 GB
Too big Get file →
Q3_K_L34.6 GB 40.5 GB
Too big Get file →
IQ4_XS34.8 GB 40.6 GB
Too big Get file →
Q4_036.9 GB 42.8 GB
Too big Get file →
Q4_K_S37.1 GB 42.9 GB
Too big Get file →
Q4_K_M39.3 GB 45.2 GB
Too big Get file →
Q5_K_S44.9 GB 50.8 GB
Too big Get file →
Q5_K_M46.2 GB 52.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (14.21 GB file, ~36.2 GB memory at 8k context). For 12 GB VRAM, IQ1_M (15.43 GB file, ~37.4 GB memory). For 24 GB VRAM, Q4_K_M (39.35 GB file, ~61.3 GB memory). Memory estimates are approximate.

What GPU do you need for airoboros-65b-gpt4-m2.0?

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: the best quant that fits is IQ3_XXS (24.7 GB file, about 46.6 GB in use).

Which airoboros-65b-gpt4-m2.0 quant should you choose?

Q4_K_M is the usual starting point for airoboros-65b-gpt4-m2.0: it balances file size and quality well. Here it is a 39.3 GB file.

If memory is tight, the smallest file is IQ1_S at 14.2 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
Parameters65B
Layers80
Trained context2,048 tokens
KV cache (fp16)2560 KB per token

Source

Quantized bymradermacher
FamilyAiroboros
Downloads (HF)3,560
Last updated2024-08-02

Frequently asked questions about airoboros-65b-gpt4-m2.0

How much VRAM does airoboros-65b-gpt4-m2.0 need?

About 61.3 GB at Q4_K_M with an 8K context window. That is the 39.3 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 airoboros-65b-gpt4-m2.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 36.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of airoboros-65b-gpt4-m2.0 GGUF?

It depends on the quant: IQ1_S is 14.2 GB, IQ1_M is 15.4 GB, IQ2_XXS is 17.5 GB, IQ2_XS is 19.3 GB, IQ2_S is 20.8 GB, IQ2_M is 22.4 GB and 14 more.

What context length does airoboros-65b-gpt4-m2.0 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 21.5 GB at 8K and 5.4 GB at 2K.

Where can I download airoboros-65b-gpt4-m2.0 GGUF?

The files are on Hugging Face in the mradermacher/airoboros-65b-gpt4-m2.0-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 airoboros-65b-gpt4-m2.0 use?

Hugging Face lists the license as cc-by-nc-4.0. 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 airoboros‑65b‑gpt4‑m2.0 on 8 GB VRAM?

Only with the smallest quant, IQ1_S, which requires about 36.2 GB of VRAM at 8k context. 8 GB VRAM is insufficient for any quant.

Is the model suitable for commercial use?

No. The CC‑BY‑NC‑4.0 license prohibits commercial use.

Does the model support image inputs?

No. The model has no vision capabilities.

Other GGUFs of airoboros-65b-gpt4-m2.0

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Airoboros models

All Airoboros →

Other large models

All large models →