MA

magnummergev2 i1

MagmergeGGUF by mradermacherUpdated 2024-12-16
Download on Hugging Face
Parameters4.51B
Context8K
Layers32
Architecturellama
Smallest quant1.2 GB
Quick answer

magnummergev2 i1 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 21 quants, from 1.2 GB (IQ1_S) to 3.7 GB (Q6_K).

4.51B param Llama model merged with IQ quantization

magnummergev2 i1 is a 4.51B parameter Llama architecture model. It was created by merging pre‑trained models using SLERP. The model supports a 8192 token context window.

Good at

  • Efficient inference with IQ quantization
  • Large context handling
  • Compact file sizes

Limits

  • No vision support
  • License not specified
  • No mixture of experts

Best for

  • Local LLM inference
  • Chatbot prototyping
  • Text generation tasks

Who it’s for. Developers and researchers who need a compact, high‑capacity Llama model for local deployment. It is suitable for those who prefer open quantization options and a large context window.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.2 GB 2.8 GB
Fits Get file →
IQ1_M1.3 GB 2.9 GB
Fits Get file →
IQ2_XXS1.4 GB 3.0 GB
Fits Get file →
IQ2_XS1.5 GB 3.1 GB
Fits Get file →
IQ2_S1.6 GB 3.2 GB
Fits Get file →
IQ2_M1.7 GB 3.3 GB
Fits Get file →
Q2_K1.8 GB 3.4 GB
Fits Get file →
IQ3_XXS1.9 GB 3.5 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_XS2.5 GB 4.1 GB
Fits Get file →
Q4_02.7 GB 4.2 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 →

For 8‑GB VRAM, use IQ1_S (1.21 GB, 2.8 GB memory) or IQ1_M (1.29 GB, 2.9 GB memory). If 12‑GB VRAM is available, IQ2_S (1.63 GB, 3.2 GB memory) or Q2_K (1.84 GB, 3.4 GB memory) are good choices. Higher‑quality Q3_K_M (2.3 GB, 3.9 GB memory) fits 16‑GB VRAM setups.

What GPU do you need for magnummergev2 i1?

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).

Which magnummergev2 i1 quant should you choose?

Q4_K_M is the usual starting point for magnummergev2 i1: it balances file size and quality well. Here it is a 2.8 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
Parameters4.51B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyMagmerge
Downloads (HF)864
Last updated2024-12-16

Frequently asked questions about magnummergev2 i1

How much VRAM does magnummergev2 i1 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 magnummergev2 i1 on an 8 GB GPU?

Yes, with Q6_K: the 3.7 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of magnummergev2 i1 GGUF?

It depends on the quant: IQ1_S is 1.2 GB, IQ1_M is 1.3 GB, IQ2_XXS is 1.4 GB, IQ2_XS is 1.5 GB, IQ2_S is 1.6 GB, IQ2_M is 1.7 GB and 15 more.

What context length does magnummergev2 i1 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 magnummergev2 i1 GGUF?

The files are on Hugging Face in the mradermacher/magnummergev2-i1-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 magnummergev2 i1 on 8 GB VRAM?

Yes, the IQ1_S quant requires about 2.8 GB memory at 8k context, which fits within 8 GB VRAM.

What is the largest context window supported?

The model supports a 8192 token context window.

Does the model support vision tasks?

No, the model does not support vision.

Other GGUFs of MagMerge2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Magmerge models

All Magmerge →

Other small models

All small models →