FI

FIPO IPL IPO Tulu2 70B i1

FipoGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters69B
Context8K
Layers80
Architecturellama
Smallest quant14.5 GB
Quick answer

FIPO IPL IPO Tulu2 70B i1 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 20 quants, from 14.5 GB (IQ1_S) to 48.8 GB (Q5_K_M).

FIPO IPL IPO Tulu2 70B i1 – a 70B llama model in GGUF format

FIPO IPL IPO Tulu2 70B i1 is a 69‑billion‑parameter llama model quantized for GGUF usage. It supports a 8192‑token context window and is available in multiple quantization levels. The model follows a specific input format with required newlines for optimal generation.

Good at

  • Large context handling
  • High‑parameter inference
  • Custom quantization options

Limits

  • No vision support
  • License not specified
  • Requires 8k context for estimates

Best for

  • Research prototyping
  • Fine‑tuning experiments
  • Low‑latency inference on GPUs

Who it’s for. Researchers and developers needing a large llama model in GGUF format. The model is suitable for those who can manage the required memory and follow the specified input formatting.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S14.5 GB 17.7 GB
Too big Get file →
IQ1_M15.9 GB 19.1 GB
Too big Get file →
IQ2_XXS18.3 GB 21.5 GB
Too big Get file →
IQ2_XS20.3 GB 23.5 GB
Too big Get file →
IQ2_S21.4 GB 24.5 GB
Too big Get file →
IQ2_M23.2 GB 26.4 GB
Too big Get file →
Q2_K25.5 GB 28.6 GB
Too big Get file →
IQ3_XXS26.6 GB 29.8 GB
Too big Get file →
IQ3_XS28.3 GB 31.5 GB
Too big Get file →
IQ3_S29.9 GB 33.1 GB
Too big Get file →
Q3_K_S29.9 GB 33.1 GB
Too big Get file →
IQ3_M30.9 GB 34.1 GB
Too big Get file →
Q3_K_M33.3 GB 36.5 GB
Too big Get file →
Q3_K_L36.1 GB 39.3 GB
Too big Get file →
IQ4_XS36.8 GB 40.0 GB
Too big Get file →
Q4_039.0 GB 42.2 GB
Too big Get file →
Q4_K_S39.2 GB 42.4 GB
Too big Get file →
Q4_K_M41.4 GB 44.6 GB
Too big Get file →
Q5_K_S47.5 GB 50.6 GB
Too big Get file →
Q5_K_M48.8 GB 51.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 14.54 GB, estimated 17.7 GB memory). For 12 GB VRAM, IQ1_M (15.94 GB, 19.1 GB). For 16 GB VRAM, IQ2_S (21.35 GB, 24.5 GB). Higher quants need more memory.

What GPU do you need for FIPO IPL IPO Tulu2 70B 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: 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 FIPO IPL IPO Tulu2 70B i1 quant should you choose?

Q4_K_M is the usual starting point for FIPO IPL IPO Tulu2 70B i1: it balances file size and quality well. Here it is a 41.4 GB file.

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 context8,192 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyFipo
Downloads (HF)762
Last updated2024-05-06

Frequently asked questions about FIPO IPL IPO Tulu2 70B i1

How much VRAM does FIPO IPL IPO Tulu2 70B i1 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 FIPO IPL IPO Tulu2 70B i1 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 FIPO IPL IPO Tulu2 70B i1 GGUF?

It depends on the quant: IQ1_S is 14.5 GB, IQ1_M is 15.9 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 and 14 more.

What context length does FIPO IPL IPO Tulu2 70B i1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.

Where can I download FIPO IPL IPO Tulu2 70B i1 GGUF?

The files are on Hugging Face in the mradermacher/FIPO-IPL-IPO-Tulu2-70B-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 this model on 8 GB VRAM?

Use the IQ1_S quant, which requires approximately 17.7 GB memory at 8k context. It will not fit on 8 GB VRAM alone.

What input format does the model expect?

Inputs must include a newline after the prompt marker. Follow the format shown in the model card for best results.

Are there any license restrictions?

No license information is provided in the model card or repository.

Other GGUFs of FIPO-IPL-IPO-Tulu2-70B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Fipo models

All Fipo →

Other large models

All large models →