SU

sustech_sus-chat-34b

SusGGUF by TheBlokeUpdated 2023-12-05
Download on Hugging Face
Parameters34.4B
Context8K
Layers60
Architecturellama
Smallest quant14.6 GB
Quick answer

sustech_sus-chat-34b needs about 23.2 GB of memory at Q4_K_M (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 14.6 GB (Q2_K) to 36.5 GB (Q8_0).

SUS-Chat-34B: 34B bilingual Chinese‑English dialogue model

SUS-Chat-34B is a 34.4B parameter LLaMA‑based model fine‑tuned on 1.4B high‑quality instruction tokens. It supports an 8K context window and excels at multi‑turn dialogues in Chinese and English.

Good at

  • High‑quality instruction following
  • Long‑context multi‑turn dialogue
  • Bilingual Chinese‑English support

Limits

  • No vision support
  • Requires 8K context for full capability
  • License is other

Best for

  • Chatbots needing 8K context
  • Multilingual instruction tasks
  • Complex reasoning dialogues

Who it’s for. Developers building bilingual chat applications or research teams needing a large‑scale instruction‑tuned model. The model is suitable for users who can allocate sufficient GPU memory for 8K context inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K14.6 GB 17.1 GB
Too big Get file →
Q3_K_S15.0 GB 17.5 GB
Too big Get file →
Q3_K_M16.6 GB 19.1 GB
Too big Get file →
Q3_K_L18.1 GB 20.7 GB
Too big Get file →
Q4_019.5 GB 22.0 GB
Too big Get file →
Q4_K_S19.5 GB 22.1 GB
Too big Get file →
Q4_K_M20.7 GB 23.2 GB
Too big Get file →
Q5_023.7 GB 26.2 GB
Too big Get file →
Q5_K_S23.7 GB 26.2 GB
Too big Get file →
Q5_K_M24.3 GB 26.8 GB
Too big Get file →
Q6_K28.2 GB 30.7 GB
Too big Get file →
Q8_036.5 GB 39.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 19.47 GB, estimated 22 GB memory). For 16 GB VRAM, Q5_0 (23.71 GB, 26.2 GB memory) or Q5_K_M (24.32 GB, 26.8 GB memory). For 24 GB VRAM, Q6_K (28.21 GB, 30.7 GB memory) is recommended. Estimates are approximate.

What GPU do you need for sustech_sus-chat-34b?

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: the best quant that fits is Q4_K_M (20.7 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.2 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.5 GB file, about 39.1 GB in use).

Which sustech_sus-chat-34b quant should you choose?

Q4_K_M is the usual starting point for sustech_sus-chat-34b: it balances file size and quality well. Here it is a 20.7 GB file.

The Q8_0 file is 36.5 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 14.6 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
Parameters34.4B
Layers60
Trained context8,192 tokens
KV cache (fp16)240 KB per token

Source

Quantized byTheBloke
FamilySus
Licenseother
Downloads (HF)1,902
Last updated2023-12-05

Frequently asked questions about sustech_sus-chat-34b

How much VRAM does sustech_sus-chat-34b need?

About 23.2 GB at Q4_K_M with an 8K context window. That is the 20.7 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 sustech_sus-chat-34b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of sustech_sus-chat-34b GGUF?

It depends on the quant: Q2_K is 14.6 GB, Q3_K_S is 15.0 GB, Q3_K_M is 16.6 GB, Q3_K_L is 18.1 GB, Q4_0 is 19.5 GB, Q4_K_S is 19.5 GB and 6 more.

What context length does sustech_sus-chat-34b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.0 GB at 8K and 2.0 GB at 8K.

Where can I download sustech_sus-chat-34b GGUF?

The files are on Hugging Face in the TheBloke/SUS-Chat-34B-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 sustech_sus-chat-34b 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 SUS-Chat-34B on 8 GB VRAM?

The Q4_0 quant requires about 22 GB memory at 8K context, so 8 GB VRAM is insufficient.

Does SUS-Chat-34B support vision tasks?

No, the model has no vision capability.

What context length does SUS-Chat-34B support?

It supports an 8K token context window.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Sus models

All Sus →

Other large models

All large models →