YI

Yiff-34B-32K-v1b

YiffGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters34.4B
Context32K
Layers60
Architecturellama
Smallest quant7.5 GB
Quick answer

Yiff-34B-32K-v1b needs about 23.2 GB of memory at Q4_K_M (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 7.5 GB (IQ1_S) to 28.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Yiff-34B-32K-v1b: 34.4B llama model with 32K context

Yiff-34B-32K-v1b is a 34.4 billion parameter llama model with a 32,768 token context window. It is available in multiple GGUF quantizations from IQ1_S to Q6_K. The model is provided by mradermacher and based on BeaverAI/Yiff-34B-32K-v1b.

Good at

  • Large context generation
  • High parameter count
  • Wide quant options

Limits

  • No license information
  • No vision support
  • Large VRAM requirement for higher quants

Best for

  • Long-form text generation
  • Research prototyping
  • Custom fine‑tuning

Who it’s for. Developers and researchers needing a large llama model with extended context. The model is suitable for those who can manage the memory demands of the higher‑quality quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.5 GB 10.0 GB
Too big Get file →
IQ1_M8.2 GB 10.7 GB
Too big Get file →
IQ2_XXS9.3 GB 11.8 GB
Too big Get file →
IQ2_XS10.3 GB 12.8 GB
Too big Get file →
IQ2_S10.9 GB 13.4 GB
Too big Get file →
IQ2_M11.8 GB 14.3 GB
Too big Get file →
Q2_K12.8 GB 15.3 GB
Too big Get file →
IQ3_XXS13.3 GB 15.8 GB
Too big Get file →
IQ3_XS14.2 GB 16.7 GB
Too big Get file →
Q3_K_S15.0 GB 17.5 GB
Too big Get file →
IQ3_S15.0 GB 17.5 GB
Too big Get file →
IQ3_M15.6 GB 18.1 GB
Too big Get file →
Q3_K_M16.7 GB 19.2 GB
Too big Get file →
Q3_K_L18.1 GB 20.7 GB
Too big Get file →
IQ4_XS18.5 GB 21.0 GB
Too big Get file →
Q4_019.5 GB 22.0 GB
Too big Get file →
Q4_K_S19.6 GB 22.1 GB
Too big Get file →
Q4_K_M20.7 GB 23.2 GB
Too big Get file →
Q5_K_S23.7 GB 26.2 GB
Too big Get file →
Q5_K_M24.3 GB 26.8 GB
Too big Get file →
Q6_K28.2 GB 30.7 GB
Too big Get file →

For 8‑GB VRAM use IQ1_S (7.5 GB file, ~10 GB memory). For 12‑GB VRAM use IQ2_XS (10.31 GB file, ~12.8 GB memory). For 24‑GB VRAM use Q4_K_M (20.66 GB file, ~23.2 GB memory).

What GPU do you need for Yiff-34B-32K-v1b?

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 IQ2_XXS (9.3 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (13.3 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (20.7 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.2 GB file, about 30.7 GB in use).

Which Yiff-34B-32K-v1b quant should you choose?

Q4_K_M is the usual starting point for Yiff-34B-32K-v1b: it balances file size and quality well. Here it is a 20.7 GB file.

If memory is tight, the smallest file is IQ1_S at 7.5 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
Parameters34.4B
Layers60
Trained context32,768 tokens
KV cache (fp16)240 KB per token

Source

Quantized bymradermacher
FamilyYiff
Downloads (HF)1,624
Last updated2024-08-02

Frequently asked questions about Yiff-34B-32K-v1b

How much VRAM does Yiff-34B-32K-v1b need?

About 23.2 GB at Q4_K_M with an 8K context window. That is the 20.7 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 Yiff-34B-32K-v1b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Yiff-34B-32K-v1b GGUF?

It depends on the quant: IQ1_S is 7.5 GB, IQ1_M is 8.2 GB, IQ2_XXS is 9.3 GB, IQ2_XS is 10.3 GB, IQ2_S is 10.9 GB, IQ2_M is 11.8 GB and 15 more.

What context length does Yiff-34B-32K-v1b support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download Yiff-34B-32K-v1b GGUF?

The files are on Hugging Face in the mradermacher/Yiff-34B-32K-v1b-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 Yiff-34B-32K-v1b on 8 GB VRAM?

Use the IQ1_S quantization, which requires about 10 GB of VRAM at 8 k context.

What is the largest quant that fits in 24 GB VRAM?

Q4_K_M fits in 24 GB VRAM, using about 23.2 GB at 8 k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of Yiff-34B-32K-v1b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Yiff models

All Yiff →

Other large models

All large models →