LL

Llama-3-Aplite-Instruct-4x8B

LlamaGGUF by mradermacherUpdated 2024-12-16
Download on Hugging Face
Parameters24.9B
Context8K
Layers32
Architecturellama
Smallest quant5.4 GB
Quick answer

Llama-3-Aplite-Instruct-4x8B needs about 16.7 GB of memory at Q4_K_M (a 15.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 5.4 GB (IQ1_S) to 20.5 GB (Q6_K).

Llama‑3‑Aplite‑Instruct‑4x8B MoE model with 24.9B parameters

Llama‑3‑Aplite‑Instruct‑4x8B is a mixture‑of‑experts model based on the Llama‑3 architecture. It contains 24.9B parameters and supports a 8192‑token context window. The model is available in multiple GGUF quantizations.

Good at

  • Coding assistance
  • Instruction following
  • Large‑context reasoning

Limits

  • Mixture‑of‑experts requires more memory
  • No vision support
  • License is other, not open source

Best for

  • Developers needing code generation
  • Researchers testing MoE models
  • Chatbots with long context

Who it’s for. This model is suited for developers and researchers who require a large‑parameter Llama‑3 variant with mixture‑of‑experts capabilities. It is ideal for applications that need extended context handling and coding support.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S5.4 GB 7.0 GB
Fits Get file →
IQ1_M5.9 GB 7.5 GB
Tight Get file →
IQ2_XXS6.8 GB 8.4 GB
Too big Get file →
IQ2_XS7.5 GB 9.1 GB
Too big Get file →
IQ2_S7.7 GB 9.3 GB
Too big Get file →
IQ2_M8.4 GB 10.0 GB
Too big Get file →
Q2_K9.3 GB 10.9 GB
Too big Get file →
IQ3_XXS9.7 GB 11.3 GB
Too big Get file →
IQ3_XS10.4 GB 12.0 GB
Too big Get file →
Q3_K_S10.9 GB 12.5 GB
Too big Get file →
IQ3_S11.0 GB 12.5 GB
Too big Get file →
IQ3_M11.1 GB 12.7 GB
Too big Get file →
Q3_K_M12.1 GB 13.7 GB
Too big Get file →
Q3_K_L13.0 GB 14.6 GB
Too big Get file →
IQ4_XS13.4 GB 15.0 GB
Too big Get file →
Q4_014.2 GB 15.8 GB
Too big Get file →
Q4_K_S14.3 GB 15.9 GB
Too big Get file →
Q4_K_M15.2 GB 16.7 GB
Too big Get file →
Q5_K_S17.2 GB 18.8 GB
Too big Get file →
Q5_K_M17.7 GB 19.3 GB
Too big Get file →
Q6_K20.5 GB 22.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 5.42 GB, estimated 7 GB memory at 8k context). For 12 GB VRAM, IQ2_XS (7.52 GB, 9.1 GB memory) or Q3_K_S (10.93 GB, 12.5 GB memory). For 16 GB VRAM, Q4_K_M (15.16 GB, 16.7 GB memory) or Q5_K_S (17.23 GB, 18.8 GB memory).

What GPU do you need for Llama-3-Aplite-Instruct-4x8B?

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: the best quant that fits is IQ1_M (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_XS (10.4 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (14.3 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (20.5 GB file, about 22.0 GB in use).

Which Llama-3-Aplite-Instruct-4x8B quant should you choose?

Q4_K_M is the usual starting point for Llama-3-Aplite-Instruct-4x8B: it balances file size and quality well. Here it is a 15.2 GB file.

If memory is tight, the smallest file is IQ1_S 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
Parameters24.9B (approximate, mixture of experts)
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licenseother
Downloads (HF)875
Last updated2024-12-16

Frequently asked questions about Llama-3-Aplite-Instruct-4x8B

How much VRAM does Llama-3-Aplite-Instruct-4x8B need?

About 16.7 GB at Q4_K_M with an 8K context window. That is the 15.2 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 Llama-3-Aplite-Instruct-4x8B on an 8 GB GPU?

Yes, with IQ1_M: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama-3-Aplite-Instruct-4x8B GGUF?

It depends on the quant: IQ1_S is 5.4 GB, IQ1_M is 5.9 GB, IQ2_XXS is 6.8 GB, IQ2_XS is 7.5 GB, IQ2_S is 7.7 GB, IQ2_M is 8.4 GB and 15 more.

What context length does Llama-3-Aplite-Instruct-4x8B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download Llama-3-Aplite-Instruct-4x8B GGUF?

The files are on Hugging Face in the mradermacher/Llama-3-Aplite-Instruct-4x8B-i1-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 Llama-3-Aplite-Instruct-4x8B 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 this model on 8 GB VRAM?

Yes, the IQ1_S quant requires about 7 GB memory at 8k context, which fits in 8 GB VRAM.

Does the model support vision tasks?

No, this model does not include vision capabilities.

What is the context length of the model?

The model supports a 8192‑token context window.

Other GGUFs of Llama-3-Aplite-Instruct-4x8B-MoE

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other medium models

All medium models →