LL

models--mergekit-community--mergekit-ties-kkhkcqw

LlamaGGUF by MaziyarPanahiUpdated 2024-06-18
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant2.5 GB
Quick answer

models--mergekit-community--mergekit-ties-kkhkcqw needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 10 quants, from 2.5 GB (Q2_K) to 7.2 GB (Q8_0).

MergeKit Ties KKHQCW, 6.74B Llama-format model

MergeKit Ties KKHQCW is a 6.74B parameter Llama model derived from InternLM2‑7B. It supports a 4096 token context window and is distributed in GGUF format. The model is available in multiple quantizations for varied hardware budgets.

Good at

  • Large context handling
  • Llama‑compatible inference
  • Versatile quantization options

Limits

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

Best for

  • Local LLM inference
  • Fine‑tuning on custom data
  • Embedding generation

Who it’s for. Developers and researchers needing a Llama‑compatible model with InternLM2 capabilities. The model is suitable for local deployment on systems with GPU or CPU support via llama.cpp or compatible libraries.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.5 GB 5.2 GB
Fits Get file →
Q3_K_S2.9 GB 5.6 GB
Fits Get file →
Q3_K_M3.3 GB 5.9 GB
Fits Get file →
Q3_K_L3.6 GB 6.2 GB
Fits Get file →
Q4_K_S3.9 GB 6.5 GB
Fits Get file →
Q4_K_M4.1 GB 6.7 GB
Fits Get file →
Q5_K_S4.7 GB 7.3 GB
Tight Get file →
Q5_K_M4.8 GB 7.4 GB
Tight Get file →
Q6_K5.5 GB 8.2 GB
Too big Get file →
Q8_07.2 GB 9.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 3.86 GB, estimated 8.7 GB memory). For 12 GB VRAM, Q5_K_M (4.78 GB, 9.6 GB memory) or Q6_K (5.53 GB, 10.3 GB memory). For larger budgets, Q8_0 (7.16 GB, 12 GB memory) offers the highest precision.

What GPU do you need for models--mergekit-community--mergekit-ties-kkhkcqw?

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_S (2.9 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).

Which models--mergekit-community--mergekit-ties-kkhkcqw quant should you choose?

Q4_K_M is the usual starting point for models--mergekit-community--mergekit-ties-kkhkcqw: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 2.5 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
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byMaziyarPanahi
FamilyLlama
Downloads (HF)1,142
Last updated2024-06-18

Frequently asked questions about models--mergekit-community--mergekit-ties-kkhkcqw

How much VRAM does models--mergekit-community--mergekit-ties-kkhkcqw need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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-ties-kkhkcqw on an 8 GB GPU?

Yes, with Q3_K_S: the 2.9 GB file needs about 7.7 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-ties-kkhkcqw GGUF?

It depends on the quant: Q2_K is 2.5 GB, Q3_K_S is 2.9 GB, Q3_K_M is 3.3 GB, Q3_K_L is 3.6 GB, Q4_K_S is 3.9 GB, Q4_K_M is 4.1 GB and 4 more.

What context length does models--mergekit-community--mergekit-ties-kkhkcqw support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download models--mergekit-community--mergekit-ties-kkhkcqw GGUF?

The files are on Hugging Face in the MaziyarPanahi/mergekit-ties-kkhkcqw-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 Q4_K_S quantization requires about 8.7 GB of VRAM at 8K context, which fits within an 8 GB GPU with some overhead.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What libraries can I use to run this GGUF model?

Supported clients include llama.cpp, llama-cpp-python, LM Studio, text-generation-webui, KoboldCpp, GPT4All, LoLLMS Web UI, Faraday.dev, candle, and ctransformers.

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Llama models

All Llama →

Other small models

All small models →