TI

tigerresearch_tigerbot-70b-chat-v2

TigerbotGGUF by TheBlokeUpdated 2023-11-30
Download on Hugging Face
Parameters69.4B
Context2K
Layers80
Architecturellama
Smallest quant29.5 GB
Quick answer

tigerresearch_tigerbot-70b-chat-v2 needs about 44.9 GB of memory at Q4_K_M (a 41.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 29.5 GB (Q2_K) to 49.1 GB (Q5_K_M).

Tigerbot 70B Chat V2 – a large llama-based chat model

Tigerbot 70B Chat V2 is a 69.4 billion parameter llama model. It supports 2048 token context and is released under the apache-2.0 license. The model is available in multiple GGUF quantisations for local inference.

Good at

  • Large context chat
  • High‑parameter reasoning
  • Open‑source compatibility

Limits

  • No vision support
  • Requires GPU for efficient inference
  • Large memory footprint

Best for

  • Chatbot development
  • Research prototyping
  • Local LLM hosting

Who it’s for. Developers and researchers who need a high‑capacity chat model that can run locally. The model is suitable for those who can allocate sufficient GPU memory and are comfortable with GGUF format.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K29.5 GB 30.7 GB
Too big Get file →
Q3_K_S30.2 GB 31.4 GB
Too big Get file →
Q3_K_M33.5 GB 34.7 GB
Too big Get file →
Q3_K_L36.4 GB 37.6 GB
Too big Get file →
Q4_039.2 GB 40.4 GB
Too big Get file →
Q4_K_S39.4 GB 40.6 GB
Too big Get file →
Q4_K_M41.7 GB 42.9 GB
Too big Get file →
Q5_047.8 GB 49.0 GB
Too big Get file →
Q5_K_S47.8 GB 49.0 GB
Too big Get file →
Q5_K_M49.1 GB 50.3 GB
Too big Get file →

For 8 GB VRAM use Q2_K (file size 29.55 GB, estimated 32.7 GB memory). For 12 GB VRAM use Q3_K_S (30.21 GB, 33.4 GB memory). For 16 GB VRAM use Q4_K_M (41.75 GB, 44.9 GB memory). Estimates are approximate.

What GPU do you need for tigerresearch_tigerbot-70b-chat-v2?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.7 GB file, about 44.9 GB in use).

Which tigerresearch_tigerbot-70b-chat-v2 quant should you choose?

Q4_K_M is the usual starting point for tigerresearch_tigerbot-70b-chat-v2: it balances file size and quality well. Here it is a 41.7 GB file.

If memory is tight, the smallest file is Q2_K at 29.5 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
Parameters69.4B
Layers80
Trained context2,048 tokens
KV cache (fp16)320 KB per token

Source

Quantized byTheBloke
FamilyTigerbot
Licenseapache-2.0
Downloads (HF)1,696
Last updated2023-11-30

Frequently asked questions about tigerresearch_tigerbot-70b-chat-v2

How much VRAM does tigerresearch_tigerbot-70b-chat-v2 need?

About 44.9 GB at Q4_K_M with an 8K context window. That is the 41.7 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 tigerresearch_tigerbot-70b-chat-v2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of tigerresearch_tigerbot-70b-chat-v2 GGUF?

It depends on the quant: Q2_K is 29.5 GB, Q3_K_S is 30.2 GB, Q3_K_M is 33.5 GB, Q3_K_L is 36.4 GB, Q4_0 is 39.2 GB, Q4_K_S is 39.4 GB and 4 more.

What context length does tigerresearch_tigerbot-70b-chat-v2 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download tigerresearch_tigerbot-70b-chat-v2 GGUF?

The files are on Hugging Face in the TheBloke/tigerbot-70B-chat-v2-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 tigerresearch_tigerbot-70b-chat-v2 use?

Hugging Face lists the license as apache-2.0. 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 Tigerbot 70B Chat V2 on 8 GB VRAM?

Use the Q2_K quantisation; it requires about 32.7 GB memory at 8k context, so 8 GB VRAM is insufficient for full inference.

Is Tigerbot 70B Chat V2 free to use?

Yes, it is released under the apache-2.0 license, which allows free use and modification.

Does the model support image inputs?

No, the model does not have vision capabilities.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Tigerbot models

All Tigerbot →

Other large models

All large models →