LO

longchat 13b 16k

LongchatGGUF by shaowenchenUpdated 2023-09-14
Download on Hugging Face
Parameters13B
Context16K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

longchat 13b 16k needs about 15.4 GB of memory at Q4_1 (a 8.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 15 quants, from 5.4 GB (Q2_K) to 26.0 GB.

Longchat 13B with 16k context, llama architecture

Longchat 13B is a 13B llama model trained with 16384 token context. It offers multiple quantization options and is suited for long‑form conversational tasks. The model does not include vision capabilities.

Good at

  • Long context conversations
  • Large language tasks
  • Customizable via quantization

Limits

  • No vision support
  • Requires at least 12.6 GB VRAM for Q2_K at 8k context
  • License not specified

Best for

  • Chatting with long documents
  • Code generation with extended context
  • Research assistants needing 16k token context

Who it’s for. Developers building chatbots that need extended context. Researchers needing a 13B llama model with 16k token capacity.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 12.6 GB
Too big Get file →
Q3_K_S5.7 GB 12.9 GB
Too big Get file →
Q3_K6.3 GB 13.5 GB
Too big Get file →
Q3_K_L6.9 GB 14.1 GB
Too big Get file →
Q4_07.4 GB 14.6 GB
Too big Get file →
Q4_K_S7.4 GB 14.6 GB
Too big Get file →
Q4_K7.9 GB 15.1 GB
Too big Get file →
Q4_18.2 GB 15.4 GB
Too big Get file →
Q5_09.0 GB 16.2 GB
Too big Get file →
Q5_K_S9.0 GB 16.2 GB
Too big Get file →
Q5_K9.2 GB 16.4 GB
Too big Get file →
Q5_19.8 GB 17.0 GB
Too big Get file →
Q6_K10.7 GB 17.9 GB
Too big Get file →
Q8_013.8 GB 21.0 GB
Too big Get file →
—26.0 GB 33.2 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (5.43 GB file, 12.6 GB memory). For 12 GB VRAM, Q4_0 (7.37 GB file, 14.6 GB memory). For 16 GB VRAM, Q5_1 (9.78 GB file, 17 GB memory).

What GPU do you need for longchat 13b 16k?

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: the best quant that fits is Q4_1 (8.2 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (26.0 GB file, about 33.2 GB in use).

Which longchat 13b 16k quant should you choose?

Q4_1 (8.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q2_K at 5.4 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
Parameters13B
Layers40
Trained context16,384 tokens
KV cache (fp16)800 KB per token

Source

Quantized byshaowenchen
FamilyLongchat
Licenseother
Downloads (HF)771
Last updated2023-09-14

Frequently asked questions about longchat 13b 16k

How much VRAM does longchat 13b 16k need?

About 15.4 GB at Q4_1 with an 8K context window. That is the 8.2 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 longchat 13b 16k on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of longchat 13b 16k GGUF?

It depends on the quant: Q2_K is 5.4 GB, Q3_K_S is 5.7 GB, Q3_K is 6.3 GB, Q3_K_L is 6.9 GB, Q4_0 is 7.4 GB, Q4_K_S is 7.4 GB and 9 more.

What context length does longchat 13b 16k support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 6.7 GB at 8K and 13.4 GB at 16K.

Where can I download longchat 13b 16k GGUF?

The files are on Hugging Face in the shaowenchen/longchat-13b-16k-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 longchat 13b 16k use?

Hugging Face lists the license as other. 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 Longchat 13B 16k on 8 GB VRAM?

No, the smallest quant Q2_K needs about 12.6 GB VRAM at 8k context, so 8 GB is insufficient.

What is the context length of this model?

The model was trained with 16384 tokens.

Does this model support vision?

No, it does not have vision capabilities.

Similar models

Browse all →

More from shaowenchen

All by shaowenchen →

More Longchat models

All Longchat →

Other medium models

All medium models →