YI

YiSM blossom5.1 40B i1

YismGGUF by mradermacherUpdated 2024-09-13
Download on Hugging Face
Parameters40B
Context4K
Layers70
Architecturellama
Smallest quant8.7 GB
Quick answer

YiSM blossom5.1 40B i1 needs about 26.8 GB of memory at Q4_K_M (a 24.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 21 quants, from 8.7 GB (IQ1_S) to 32.8 GB (Q6_K).

YiSM blossom5.1 40B i1 – 40B parameter Llama model in GGUF format

YiSM blossom5.1 40B i1 is a 40B parameter Llama architecture model. It supports a 4096 token context window and is released under the Apache‑2.0 license. The model is available in multiple quantizations for different memory budgets.

Good at

  • Large‑scale text generation
  • Contextual understanding up to 4096 tokens
  • High‑capacity language modeling

Limits

  • No vision support
  • Requires significant VRAM for higher quants
  • No mixture of experts

Best for

  • Research on large language models
  • Fine‑tuning for domain‑specific tasks
  • Benchmarking quantization techniques

Who it’s for. Researchers and developers needing a large Llama‑style model for text generation and analysis. The model is suitable for those who can manage the memory requirements of 40B parameter models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S8.7 GB 10.3 GB
Too big Get file →
IQ1_M9.5 GB 11.1 GB
Too big Get file →
IQ2_XXS10.8 GB 12.5 GB
Too big Get file →
IQ2_XS11.9 GB 13.6 GB
Too big Get file →
IQ2_S12.6 GB 14.3 GB
Too big Get file →
IQ2_M13.7 GB 15.3 GB
Too big Get file →
Q2_K14.9 GB 16.5 GB
Too big Get file →
IQ3_XXS15.5 GB 17.1 GB
Too big Get file →
IQ3_XS16.5 GB 18.2 GB
Too big Get file →
Q3_K_S17.4 GB 19.0 GB
Too big Get file →
IQ3_S17.4 GB 19.1 GB
Too big Get file →
IQ3_M18.1 GB 19.7 GB
Too big Get file →
Q3_K_M19.3 GB 21.0 GB
Too big Get file →
Q3_K_L21.1 GB 22.7 GB
Too big Get file →
IQ4_XS21.5 GB 23.1 GB
Too big Get file →
Q4_022.7 GB 24.4 GB
Too big Get file →
Q4_K_S22.8 GB 24.4 GB
Too big Get file →
Q4_K_M24.0 GB 25.6 GB
Too big Get file →
Q5_K_S27.5 GB 29.2 GB
Too big Get file →
Q5_K_M28.2 GB 29.9 GB
Too big Get file →
Q6_K32.8 GB 34.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (8.67 GB file, 11.5 GB memory at 8k context). For 12 GB VRAM, IQ1_M (9.46 GB file, 12.3 GB memory). For 16 GB VRAM, IQ2_XS (11.95 GB file, 14.8 GB memory).

What GPU do you need for YiSM blossom5.1 40B 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: the best quant that fits is IQ1_S (8.7 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ2_S (12.6 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q3_K_L (21.1 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (28.2 GB file, about 31.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (32.8 GB file, about 35.6 GB in use).

Which YiSM blossom5.1 40B i1 quant should you choose?

Q4_K_M is the usual starting point for YiSM blossom5.1 40B i1: it balances file size and quality well. Here it is a 24.0 GB file.

If memory is tight, the smallest file is IQ1_S at 8.7 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
Parameters40B
Layers70
Trained context4,096 tokens
KV cache (fp16)280 KB per token

Source

Quantized bymradermacher
FamilyYism
Licenseapache-2.0
Downloads (HF)708
Last updated2024-09-13

Frequently asked questions about YiSM blossom5.1 40B i1

How much VRAM does YiSM blossom5.1 40B i1 need?

About 26.8 GB at Q4_K_M with an 8K context window. That is the 24.0 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 YiSM blossom5.1 40B i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of YiSM blossom5.1 40B i1 GGUF?

It depends on the quant: IQ1_S is 8.7 GB, IQ1_M is 9.5 GB, IQ2_XXS is 10.8 GB, IQ2_XS is 11.9 GB, IQ2_S is 12.6 GB, IQ2_M is 13.7 GB and 15 more.

What context length does YiSM blossom5.1 40B 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 2.3 GB at 8K and 1.2 GB at 4K.

Where can I download YiSM blossom5.1 40B i1 GGUF?

The files are on Hugging Face in the mradermacher/YiSM-blossom5.1-40B-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 YiSM blossom5.1 40B i1 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 YiSM blossom5.1 40B i1 on 8 GB VRAM?

Use the IQ1_S quantization, which requires 11.5 GB memory at 8k context and has a file size of 8.67 GB.

Is this model licensed for commercial use?

Yes, it is released under the Apache‑2.0 license, which permits commercial use.

Does the model support vision tasks?

No, the model does not have vision capabilities.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Yism models

All Yism →

Other large models

All large models →