LL

LLama 3.1 4B TitanFusion

LlamaGGUF by mradermacherUpdated 2024-09-18
Download on Hugging Face
Parameters4.51B
Context128K
Layers32
Architecturellama
Smallest quant1.8 GB
Quick answer

LLama 3.1 4B TitanFusion needs about 4.4 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 1.8 GB (Q2_K) to 9.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

LLama 3.1 4B TitanFusion – a 4.51B parameter merge model

LLama 3.1 4B TitanFusion is a 4.51B parameter model merged from Magpie-Align and MagpieLM-4B-Chat-v0.1. It supports a 131072 token context window and is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Efficient inference with low‑bit quants
  • Stable language generation

Limits

  • No vision support
  • License not specified
  • Requires 8k context for memory estimates

Best for

  • Chatbots needing long context
  • Fine‑tuning on custom data
  • Local inference on mid‑range GPUs

Who it’s for. Developers and researchers who need a compact Llama model with a large context window and multiple quantization options for local deployment. The model is suitable for those who prefer open‑source merges and can manage the lack of a formal license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.8 GB 3.4 GB
Fits Get file →
IQ3_XS2.0 GB 3.6 GB
Fits Get file →
Q3_K_S2.1 GB 3.7 GB
Fits Get file →
IQ3_S2.1 GB 3.7 GB
Fits Get file →
IQ3_M2.2 GB 3.8 GB
Fits Get file →
Q3_K_M2.3 GB 3.9 GB
Fits Get file →
Q3_K_L2.5 GB 4.0 GB
Fits Get file →
IQ4_XS2.6 GB 4.1 GB
Fits Get file →
Q4_K_S2.7 GB 4.2 GB
Fits Get file →
Q4_K_M2.8 GB 4.4 GB
Fits Get file →
Q5_K_S3.2 GB 4.7 GB
Fits Get file →
Q5_K_M3.2 GB 4.8 GB
Fits Get file →
Q6_K3.7 GB 5.3 GB
Fits Get file →
Q8_04.8 GB 6.4 GB
Fits Get file →
F169.0 GB 10.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.78 GB, estimated 4.4 GB memory). For 12 GB VRAM, Q5_K_M (3.23 GB, 4.8 GB memory) or Q6_K (3.71 GB, 5.3 GB memory). For 16 GB VRAM, Q8_0 (4.8 GB, 6.4 GB memory) or F16 (9.03 GB, 10.6 GB memory).

What GPU do you need for LLama 3.1 4B TitanFusion?

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 Q3_K_L (2.5 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.7 GB file, about 5.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.8 GB file, about 6.4 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (9.0 GB file, about 10.6 GB in use).

Which LLama 3.1 4B TitanFusion quant should you choose?

Q4_K_M is the usual starting point for LLama 3.1 4B TitanFusion: it balances file size and quality well. Here it is a 2.8 GB file.

The Q8_0 file is 4.8 GB, about 1.7 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 1.8 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
Parameters4.51B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyLlama
Downloads (HF)797
Last updated2024-09-18

Frequently asked questions about LLama 3.1 4B TitanFusion

How much VRAM does LLama 3.1 4B TitanFusion need?

About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.8 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 3.1 4B TitanFusion on an 8 GB GPU?

Yes, with Q8_0: the 4.8 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LLama 3.1 4B TitanFusion GGUF?

It depends on the quant: Q2_K is 1.8 GB, IQ3_XS is 2.0 GB, Q3_K_S is 2.1 GB, IQ3_S is 2.1 GB, IQ3_M is 2.2 GB, Q3_K_M is 2.3 GB and 9 more.

What context length does LLama 3.1 4B TitanFusion support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download LLama 3.1 4B TitanFusion GGUF?

The files are on Hugging Face in the mradermacher/LLama-3.1-4B-TitanFusion-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run LLama 3.1 4B TitanFusion on 8 GB VRAM?

Yes, use Q4_K_M or Q4_K_S which require about 4.4 GB or 4.2 GB memory at 8k context.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What is the maximum context length?

The model supports up to 131072 tokens of context.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →