LL

openchat-3.6-8b-20240522

LlamaGGUF by bartowskiUpdated 2024-05-25
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

openchat-3.6-8b-20240522 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 23 quants, from 2.0 GB (IQ1_S) to 32.1 GB (F32).

8B Llama model optimized for llama.cpp

openchat-3.6-8b-20240522 is an 8.03B parameter Llama model. It supports a 8192 token context window and is released under the llama3 license. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • LLM chat tasks
  • Text generation

Limits

  • No vision support
  • Requires 8.03B parameters
  • License limited to llama3

Best for

  • Chatbot development
  • Content drafting
  • Code assistance

Who it’s for. Developers and researchers needing a lightweight Llama model for local inference. The model is suitable for users with GPU or CPU resources that can accommodate the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ1_M2.2 GB 3.7 GB
Fits Get file →
IQ2_XXS2.4 GB 4.0 GB
Fits Get file →
IQ2_XS2.6 GB 4.2 GB
Fits Get file →
IQ2_S2.8 GB 4.3 GB
Fits Get file →
IQ2_M2.9 GB 4.5 GB
Fits Get file →
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XXS3.3 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.4 GB 6.0 GB
Fits Get file →
IQ4_NL4.7 GB 6.3 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
F3232.1 GB 33.7 GB
Too big Get file →

For 8 GB VRAM, use IQ2_S (file size 2.76 GB, memory 4.3 GB). For 16 GB VRAM, use Q4_K_M (file size 4.92 GB, memory 6.5 GB). For 32 GB VRAM, use Q5_K_M (file size 5.73 GB, memory 7.3 GB).

What GPU do you need for openchat-3.6-8b-20240522?

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: the best quant that fits is IQ2_XXS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 48 GB VRAM: the best quant that fits is F32 (32.1 GB file, about 33.7 GB in use).

Which openchat-3.6-8b-20240522 quant should you choose?

Q4_K_M is the usual starting point for openchat-3.6-8b-20240522: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 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 IQ1_S at 2.0 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
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bybartowski
FamilyLlama
Licensellama3
Downloads (HF)784
Last updated2024-05-25

Frequently asked questions about openchat-3.6-8b-20240522

How much VRAM does openchat-3.6-8b-20240522 need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 openchat-3.6-8b-20240522 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of openchat-3.6-8b-20240522 GGUF?

It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB, IQ2_M is 2.9 GB and 17 more.

What context length does openchat-3.6-8b-20240522 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download openchat-3.6-8b-20240522 GGUF?

The files are on Hugging Face in the bartowski/openchat-3.6-8b-20240522-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 openchat-3.6-8b-20240522 use?

Hugging Face lists the license as llama3. 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 openchat-3.6-8b on 8 GB VRAM?

Yes, use a quant such as IQ2_S which requires about 4.3 GB of VRAM at 8 k context.

What quant gives the best quality?

The Q8_0 quant offers the highest quality but needs about 10.1 GB of VRAM at 8 k context.

Is this model suitable for CPU inference?

Yes, I-quant versions like IQ3_M run on CPU, though they are slower than K-quant equivalents.

Other GGUFs of Meta-Llama-3-8B

Similar models

Browse all →

More from bartowski

All by bartowski →

More Llama models

All Llama →

Other small models

All small models →