AQ

AquilaChat2 34B 16K

AquilachatGGUF by mradermacherUpdated 2024-11-21
Download on Hugging Face
Parameters33.7B
Context16K
Layers60
Architecturellama
Smallest quant12.6 GB
Quick answer

AquilaChat2 34B 16K needs about 22.8 GB of memory at Q4_K_M (a 20.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 12.6 GB (Q2_K) to 35.8 GB (Q8_0).

AquilaChat2 34B 16K – large‑scale chat model with 16K context

AquilaChat2 34B 16K is a 33.7‑billion‑parameter LLM based on the AquilaChat2 family. It supports a 16384‑token context window and is available in multiple GGUF quantizations. The model is open‑source under the BAAI Aquila Model Licence Agreement.

Good at

  • Long‑form text generation
  • Instruction following
  • Multi‑turn conversation

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • License is other

Best for

  • Chatbots needing 16K context
  • Content drafting with long passages
  • Research prototyping

Who it’s for. Developers and researchers who need a high‑capacity chat model with extended context. The model is suitable for applications that can accommodate the memory requirements of the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.6 GB 15.1 GB
Too big Get file →
IQ3_XS14.0 GB 16.5 GB
Too big Get file →
Q3_K_S14.7 GB 17.2 GB
Too big Get file →
IQ3_S14.8 GB 17.3 GB
Too big Get file →
IQ3_M15.2 GB 17.7 GB
Too big Get file →
Q3_K_M16.3 GB 18.9 GB
Too big Get file →
Q3_K_L17.7 GB 20.3 GB
Too big Get file →
IQ4_XS18.3 GB 20.8 GB
Too big Get file →
Q4_K_S19.3 GB 21.8 GB
Too big Get file →
Q4_K_M20.3 GB 22.8 GB
Too big Get file →
Q5_K_S23.3 GB 25.8 GB
Too big Get file →
Q5_K_M23.9 GB 26.4 GB
Too big Get file →
Q6_K27.6 GB 30.2 GB
Too big Get file →
Q8_035.8 GB 38.3 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (12.6 GB file, ~15.1 GB memory at 8K context). For 12 GB VRAM, Q3_K_S (14.73 GB file, ~17.2 GB memory). For 16 GB VRAM, Q4_K_M (20.33 GB file, ~22.8 GB memory). Estimates are approximate.

What GPU do you need for AquilaChat2 34B 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 Q2_K (12.6 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (20.3 GB file, about 22.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (27.6 GB file, about 30.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (35.8 GB file, about 38.3 GB in use).

Which AquilaChat2 34B 16K quant should you choose?

Q4_K_M is the usual starting point for AquilaChat2 34B 16K: it balances file size and quality well. Here it is a 20.3 GB file.

The Q8_0 file is 35.8 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 12.6 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
Parameters33.7B
Layers60
Trained context16,384 tokens
KV cache (fp16)240 KB per token

Source

Quantized bymradermacher
Licenseother
Downloads (HF)784
Last updated2024-11-21

Frequently asked questions about AquilaChat2 34B 16K

How much VRAM does AquilaChat2 34B 16K need?

About 22.8 GB at Q4_K_M with an 8K context window. That is the 20.3 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 AquilaChat2 34B 16K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of AquilaChat2 34B 16K GGUF?

It depends on the quant: Q2_K is 12.6 GB, IQ3_XS is 14.0 GB, Q3_K_S is 14.7 GB, IQ3_S is 14.8 GB, IQ3_M is 15.2 GB, Q3_K_M is 16.3 GB and 8 more.

What context length does AquilaChat2 34B 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 2.0 GB at 8K and 4.0 GB at 16K.

Where can I download AquilaChat2 34B 16K GGUF?

The files are on Hugging Face in the mradermacher/AquilaChat2-34B-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 AquilaChat2 34B 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 AquilaChat2 34B 16K on 8 GB VRAM?

Use the Q2_K quant, which requires about 15.1 GB of VRAM at 8K context. 8 GB VRAM is insufficient for this quant.

Does the model support image input?

No, AquilaChat2 34B 16K is a text‑only model with no vision capabilities.

What license applies to this model?

The model is released under the BAAI Aquila Model Licence Agreement, which is classified as "other".

Other GGUFs of AquilaChat2-34B-16K

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Aquilachat models

All Aquilachat →

Other medium models

All medium models →