LL

models--mergekit-community--mergekit-passthrough-kijjzjp

LlamaGGUF by MaziyarPanahiUpdated 2024-06-16
Download on Hugging Face
Parameters11.5B
Context8K
Layers48
Architecturellama
Smallest quant4.5 GB
Quick answer

models--mergekit-community--mergekit-passthrough-kijjzjp needs about 9.1 GB of memory at Q4_K_M (a 7.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 10 quants, from 4.5 GB (Q2_K) to 12.2 GB (Q8_0).

11.5B Llama model in GGUF format

This GGUF model contains 11.5 billion parameters and supports a 8192 token context window. It is a direct conversion of the Llama architecture and is compatible with llama.cpp and related tools. No specific license is provided.

Good at

  • Large context handling
  • Versatile text generation
  • Compatible with llama.cpp ecosystem

Limits

  • No vision support
  • Requires 8k context for estimates
  • License unspecified

Best for

  • Local inference on GPU
  • Fine‑tuning with llama.cpp
  • Embedding generation

Who it’s for. Developers and researchers who need a large Llama model for local inference or fine‑tuning. The model is suitable for projects that rely on the GGUF format and llama.cpp ecosystem.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.5 GB 6.6 GB
Fits Get file →
Q3_K_S5.2 GB 7.3 GB
Tight Get file →
Q3_K_M5.7 GB 7.8 GB
Tight Get file →
Q3_K_L6.2 GB 8.3 GB
Too big Get file →
Q4_K_S6.7 GB 8.8 GB
Too big Get file →
Q4_K_M7.0 GB 9.1 GB
Too big Get file →
Q5_K_S8.0 GB 10.1 GB
Too big Get file →
Q5_K_M8.2 GB 10.3 GB
Too big Get file →
Q6_K9.5 GB 11.6 GB
Too big Get file →
Q8_012.2 GB 14.4 GB
Too big Get file →

For 8 GB VRAM, Q2_K (4.46 GB, 6.6 GB memory) is the lightest option. If 12 GB VRAM is available, Q4_K_M (7.01 GB, 9.1 GB memory) offers a good balance of size and quality. Higher quants such as Q5_K_M or Q8_0 require 14.4 GB or more and are not recommended for limited memory setups.

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

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 Q3_K_M (5.7 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (9.5 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (12.2 GB file, about 14.4 GB in use).

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

Q4_K_M is the usual starting point for models--mergekit-community--mergekit-passthrough-kijjzjp: it balances file size and quality well. Here it is a 7.0 GB file.

The Q8_0 file is 12.2 GB, about 1.7 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 4.5 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
Parameters11.5B
Layers48
Trained context8,192 tokens
KV cache (fp16)192 KB per token

Source

Quantized byMaziyarPanahi
FamilyLlama
Downloads (HF)1,339
Last updated2024-06-16

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

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

About 9.1 GB at Q4_K_M with an 8K context window. That is the 7.0 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 models--mergekit-community--mergekit-passthrough-kijjzjp on an 8 GB GPU?

Yes, with Q3_K_M: the 5.7 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: Q2_K is 4.5 GB, Q3_K_S is 5.2 GB, Q3_K_M is 5.7 GB, Q3_K_L is 6.2 GB, Q4_K_S is 6.7 GB, Q4_K_M is 7.0 GB and 4 more.

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

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.

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

The files are on Hugging Face in the MaziyarPanahi/mergekit-passthrough-kijjzjp-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 Q4_K_M on 8 GB VRAM?

No, Q4_K_M requires approximately 9.1 GB of VRAM at 8k context, exceeding an 8 GB limit.

What is the context length?

The model supports a 8192 token context window.

Is there a license?

No license information is provided for this model.

Other GGUFs of llama-3-lust-8b-step-748

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Llama models

All Llama →

Other medium models

All medium models →