AC

AceGPT-v1.5-13B-Chat

AcegptGGUF by mradermacherUpdated 2024-06-23
Download on Hugging Face
Parameters13.1B
Context4K
Layers40
Architecturellama
Smallest quant4.9 GB
Quick answer

AceGPT-v1.5-13B-Chat needs about 15.2 GB of memory at Q4_K_M (a 8.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 4.9 GB (Q2_K) to 14.0 GB (Q8_0).

AceGPT‑v1.5‑13B‑Chat – Arabic‑focused 13B LLaMA2 chat model

AceGPT‑v1.5‑13B‑Chat is a 13.1B‑parameter LLaMA2‑based chat model fine‑tuned for Arabic text. It supports 4096‑token context and is released under Apache‑2.0. The model is available in multiple GGUF quantizations.

Good at

  • Arabic dialogue
  • Text generation
  • Fine‑tuned Arabic tasks

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No non‑Arabic language focus

Best for

  • Arabic customer support
  • Arabic content creation
  • Arabic QA systems

Who it’s for. Developers building Arabic‑centric chatbots or content tools. Researchers needing a large Arabic LLM for fine‑tuning or evaluation. Teams with GPU memory between 12–22 GB who can run GGUF quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.9 GB 8.8 GB
Too big Get file →
IQ3_XS5.4 GB 9.3 GB
Too big Get file →
IQ3_S5.7 GB 9.6 GB
Too big Get file →
Q3_K_S5.7 GB 9.6 GB
Too big Get file →
IQ3_M6.1 GB 9.9 GB
Too big Get file →
Q3_K_M6.4 GB 10.3 GB
Too big Get file →
Q3_K_L7.0 GB 10.9 GB
Too big Get file →
IQ4_XS7.1 GB 11.0 GB
Too big Get file →
Q4_K_S7.5 GB 11.4 GB
Too big Get file →
Q4_K_M8.0 GB 11.8 GB
Too big Get file →
Q5_K_S9.1 GB 12.9 GB
Too big Get file →
Q5_K_M9.3 GB 13.2 GB
Too big Get file →
Q6_K10.8 GB 14.6 GB
Too big Get file →
Q8_014.0 GB 17.8 GB
Too big Get file →

For 12–14 GB VRAM, use Q2_K (4.93 GB, 12.1 GB memory) or IQ3_XS (5.44 GB, 12.7 GB). For 15–18 GB VRAM, Q4_K_M (7.96 GB, 15.2 GB) or Q5_K_S (9.07 GB, 16.3 GB). For 20+ GB VRAM, Q6_K (10.79 GB, 18 GB) or Q8_0 (13.97 GB, 21.2 GB). Estimates are approximate.

What GPU do you need for AceGPT-v1.5-13B-Chat?

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_K_M (8.0 GB file, about 15.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.0 GB file, about 21.2 GB in use).

Which AceGPT-v1.5-13B-Chat quant should you choose?

Q4_K_M is the usual starting point for AceGPT-v1.5-13B-Chat: it balances file size and quality well. Here it is a 8.0 GB file.

The Q8_0 file is 14.0 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 4.9 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
Parameters13.1B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymradermacher
FamilyAcegpt
Licenseapache-2.0
Downloads (HF)790
Last updated2024-06-23

Frequently asked questions about AceGPT-v1.5-13B-Chat

How much VRAM does AceGPT-v1.5-13B-Chat need?

About 15.2 GB at Q4_K_M with an 8K context window. That is the 8.0 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 AceGPT-v1.5-13B-Chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of AceGPT-v1.5-13B-Chat GGUF?

It depends on the quant: Q2_K is 4.9 GB, IQ3_XS is 5.4 GB, IQ3_S is 5.7 GB, Q3_K_S is 5.7 GB, IQ3_M is 6.1 GB, Q3_K_M is 6.4 GB and 8 more.

What context length does AceGPT-v1.5-13B-Chat support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download AceGPT-v1.5-13B-Chat GGUF?

The files are on Hugging Face in the mradermacher/AceGPT-v1.5-13B-Chat-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 AceGPT-v1.5-13B-Chat 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 AceGPT‑v1.5‑13B‑Chat on 8 GB VRAM?

No, the smallest quant requires 12.1 GB memory at 8k context. 8 GB VRAM is insufficient.

Does the model support vision tasks?

No, it accepts text input only and outputs text.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Acegpt models

All Acegpt →

Other medium models

All medium models →