LL

Meta Llama 3 4B Mlp Pruned

LlamaGGUF by mradermacherUpdated 2025-01-26
Download on Hugging Face
Parameters4B
Context8K
Layers32
Architecturellama
Smallest quant1.2 GB
Quick answer

Meta Llama 3 4B Mlp Pruned needs about 4.1 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.2 GB (IQ1_S) to 3.3 GB (Q6_K).

Meta Llama 3 4B Mlp Pruned is a 4B-parameter Llama model in GGUF format, quantized by mradermacher. Its trained context length is 8K tokens. The repository has 24 quant files, from 1.2 GB (IQ1_S) to 3.3 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.2 GB 2.8 GB
Fits Get file →
IQ1_M1.3 GB 2.8 GB
Fits Get file →
IQ2_XXS1.3 GB 2.9 GB
Fits Get file →
IQ2_XS1.4 GB 3.0 GB
Fits Get file →
IQ2_S1.6 GB 3.1 GB
Fits Get file →
Q2_K_S1.6 GB 3.2 GB
Fits Get file →
IQ2_M1.6 GB 3.2 GB
Fits Get file →
Q2_K1.7 GB 3.3 GB
Fits Get file →
IQ3_XXS1.7 GB 3.3 GB
Fits Get file →
IQ3_XS1.9 GB 3.5 GB
Fits Get file →
Q3_K_S1.9 GB 3.5 GB
Fits Get file →
IQ3_S2.0 GB 3.5 GB
Fits Get file →
IQ3_M2.0 GB 3.6 GB
Fits Get file →
Q3_K_M2.1 GB 3.7 GB
Fits Get file →
Q3_K_L2.2 GB 3.8 GB
Fits Get file →
IQ4_XS2.3 GB 3.9 GB
Fits Get file →
Q4_02.4 GB 4.0 GB
Fits Get file →
Q4_K_S2.4 GB 4.0 GB
Fits Get file →
IQ4_NL2.4 GB 4.0 GB
Fits Get file →
Q4_K_M2.5 GB 4.1 GB
Fits Get file →
Q4_12.6 GB 4.2 GB
Fits Get file →
Q5_K_S2.8 GB 4.4 GB
Fits Get file →
Q5_K_M2.9 GB 4.4 GB
Fits Get file →
Q6_K3.3 GB 4.9 GB
Fits Get file →

What GPU do you need for Meta Llama 3 4B Mlp Pruned?

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: the best quant that fits is IQ4_NL (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.3 GB file, about 4.9 GB in use).

Which Meta Llama 3 4B Mlp Pruned quant should you choose?

Q4_K_M is the usual starting point for Meta Llama 3 4B Mlp Pruned: it balances file size and quality well. Here it is a 2.5 GB file.

If memory is tight, the smallest file is IQ1_S at 1.2 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
Parameters4B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyLlama
Downloads (HF)163
Last updated2025-01-26

Frequently asked questions about Meta Llama 3 4B Mlp Pruned

How much VRAM does Meta Llama 3 4B Mlp Pruned need?

About 4.1 GB at Q4_K_M with an 8K context window. That is the 2.5 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 Meta Llama 3 4B Mlp Pruned on an 8 GB GPU?

Yes, with Q6_K: the 3.3 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Meta Llama 3 4B Mlp Pruned GGUF?

It depends on the quant: IQ1_S is 1.2 GB, IQ1_M is 1.3 GB, IQ2_XXS is 1.3 GB, IQ2_XS is 1.4 GB, IQ2_S is 1.6 GB, Q2_K_S is 1.6 GB and 18 more.

What context length does Meta Llama 3 4B Mlp Pruned 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 Meta Llama 3 4B Mlp Pruned GGUF?

The files are on Hugging Face in the mradermacher/Meta-Llama-3-4B-mlp-pruned-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Meta-Llama-3-4B-mlp-pruned

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →