LL

models--mergekit-community--mergekit-passthrough-yqhuxcv

LlamaGGUF by MaziyarPanahiUpdated 2024-06-15
Download on Hugging Face
Parameters44.9B
Context8K
Layers50
Architecturellama
Smallest quant16.9 GB
Quick answer

models--mergekit-community--mergekit-passthrough-yqhuxcv needs about 29.3 GB of memory at Q4_K_M (a 27.1 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 10 quants, from 16.9 GB (Q2_K) to 47.7 GB (Q8_0).

models--mergekit-community--mergekit-passthrough-yqhuxcv is a 44.9B-parameter Llama model in GGUF format, quantized by MaziyarPanahi. Its trained context length is 8K tokens. The repository has 10 quant files, from 16.9 GB (Q2_K) to 47.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K16.9 GB 19.1 GB
Too big Get file →
Q3_K_S19.7 GB 21.9 GB
Too big Get file →
Q3_K_M21.9 GB 24.0 GB
Too big Get file →
Q3_K_L23.7 GB 25.9 GB
Too big Get file →
Q4_K_S25.7 GB 27.9 GB
Too big Get file →
Q4_K_M27.1 GB 29.3 GB
Too big Get file →
Q5_K_S31.0 GB 33.2 GB
Too big Get file →
Q5_K_M31.8 GB 34.0 GB
Too big Get file →
Q6_K36.8 GB 39.0 GB
Too big Get file →
Q8_047.7 GB 49.9 GB
Too big Get file →

What GPU do you need for models--mergekit-community--mergekit-passthrough-yqhuxcv?

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 Q3_K_M (21.9 GB file, about 24.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (27.1 GB file, about 29.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (36.8 GB file, about 39.0 GB in use).

Which models--mergekit-community--mergekit-passthrough-yqhuxcv quant should you choose?

Q4_K_M is the usual starting point for models--mergekit-community--mergekit-passthrough-yqhuxcv: it balances file size and quality well. Here it is a 27.1 GB file.

The Q8_0 file is 47.7 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 16.9 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
Parameters44.9B
Layers50
Trained context8,192 tokens
KV cache (fp16)200 KB per token

Source

Quantized byMaziyarPanahi
FamilyLlama
Downloads (HF)295
Last updated2024-06-15

Frequently asked questions about models--mergekit-community--mergekit-passthrough-yqhuxcv

How much VRAM does models--mergekit-community--mergekit-passthrough-yqhuxcv need?

About 29.3 GB at Q4_K_M with an 8K context window. That is the 27.1 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 models--mergekit-community--mergekit-passthrough-yqhuxcv on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of models--mergekit-community--mergekit-passthrough-yqhuxcv GGUF?

It depends on the quant: Q2_K is 16.9 GB, Q3_K_S is 19.7 GB, Q3_K_M is 21.9 GB, Q3_K_L is 23.7 GB, Q4_K_S is 25.7 GB, Q4_K_M is 27.1 GB and 4 more.

What context length does models--mergekit-community--mergekit-passthrough-yqhuxcv support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.7 GB at 8K and 1.7 GB at 8K.

Where can I download models--mergekit-community--mergekit-passthrough-yqhuxcv GGUF?

The files are on Hugging Face in the MaziyarPanahi/mergekit-passthrough-yqhuxcv-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Llama3-OpenBioLLM-70B

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Llama models

All Llama →

Other large models

All large models →