ST

stripped marcoroni 70b 2 i1

StrippedGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters20.2B
Context4K
Layers23
Architecturellama
Smallest quant5.2 GB
Quick answer

stripped marcoroni 70b 2 i1 needs about 14.2 GB of memory at Q4_K_M (a 13.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 19 quants, from 5.2 GB (IQ1_S) to 17.4 GB (Q6_K).

Stripped Marcoroni 70B 2 i1 – 20.2B parameter LLaMA model

Stripped Marcoroni 70B 2 i1 is a 20.2B parameter LLaMA model with a 4096 token context window. It is available in multiple GGUF quantizations from IQ1_S to Q6_K. The model is provided by mradermacher and derived from ibivibiv/stripped_marcoroni_70b_2.

Good at

  • Large context generation
  • High token throughput
  • Efficient inference with quantization

Limits

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

Best for

  • Chat applications with long context
  • Fine‑tuning on domain data
  • Batch inference on GPU

Who it’s for. Developers and researchers needing a large LLaMA variant with flexible quantization options. Suitable for those who can manage the memory requirements and do not need vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S5.2 GB 6.1 GB
Fits Get file →
IQ2_XXS6.3 GB 7.2 GB
Fits Get file →
IQ2_XS6.9 GB 7.8 GB
Tight Get file →
IQ2_S7.2 GB 8.1 GB
Too big Get file →
IQ2_M7.7 GB 8.6 GB
Too big Get file →
Q2_K8.3 GB 9.2 GB
Too big Get file →
IQ3_XXS8.7 GB 9.6 GB
Too big Get file →
IQ3_XS9.1 GB 10.0 GB
Too big Get file →
Q3_K_S9.6 GB 10.5 GB
Too big Get file →
IQ3_S9.6 GB 10.5 GB
Too big Get file →
IQ3_M9.9 GB 10.8 GB
Too big Get file →
Q3_K_M10.6 GB 11.5 GB
Too big Get file →
Q3_K_L11.5 GB 12.3 GB
Too big Get file →
IQ4_XS11.7 GB 12.6 GB
Too big Get file →
Q4_K_S12.3 GB 13.2 GB
Too big Get file →
Q4_K_M13.0 GB 13.8 GB
Too big Get file →
Q5_K_S14.8 GB 15.6 GB
Too big Get file →
Q5_K_M15.1 GB 16.0 GB
Too big Get file →
Q6_K17.4 GB 18.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (5.21 GB file, 6.5 GB memory). For 12 GB VRAM, Q4_K_M (12.96 GB file, 14.2 GB memory) is a good balance. For 16 GB VRAM, Q5_K_M (15.12 GB file, 16.4 GB memory) provides higher quality.

What GPU do you need for stripped marcoroni 70b 2 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: the best quant that fits is IQ2_XXS (6.3 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q3_K_M (10.6 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_S (14.8 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (17.4 GB file, about 18.7 GB in use).

Which stripped marcoroni 70b 2 i1 quant should you choose?

Q4_K_M is the usual starting point for stripped marcoroni 70b 2 i1: it balances file size and quality well. Here it is a 13.0 GB file.

If memory is tight, the smallest file is IQ1_S at 5.2 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
Parameters20.2B
Layers23
Trained context4,096 tokens
KV cache (fp16)92 KB per token

Source

Quantized bymradermacher
FamilyStripped
Downloads (HF)536
Last updated2024-05-06

Frequently asked questions about stripped marcoroni 70b 2 i1

How much VRAM does stripped marcoroni 70b 2 i1 need?

About 14.2 GB at Q4_K_M with an 8K context window. That is the 13.0 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 stripped marcoroni 70b 2 i1 on an 8 GB GPU?

Yes, with IQ2_XXS: the 6.3 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of stripped marcoroni 70b 2 i1 GGUF?

It depends on the quant: IQ1_S is 5.2 GB, IQ2_XXS is 6.3 GB, IQ2_XS is 6.9 GB, IQ2_S is 7.2 GB, IQ2_M is 7.7 GB, Q2_K is 8.3 GB and 13 more.

What context length does stripped marcoroni 70b 2 i1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.4 GB at 4K.

Where can I download stripped marcoroni 70b 2 i1 GGUF?

The files are on Hugging Face in the mradermacher/stripped_marcoroni_70b_2-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?

Yes, the IQ1_S quant uses 6.5 GB memory at 8k context, fitting within 8 GB VRAM.

Does the model support vision tasks?

No, the model has no vision capabilities.

What is the context length of this model?

The model supports a 4096 token context window.

Other GGUFs of stripped_marcoroni_70b_2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Stripped models

All Stripped →

Other medium models

All medium models →