LU

Lumosia v2 MoE 4x10.7 i1

LumosiaGGUF by mradermacherUpdated 2024-12-16
Download on Hugging Face
Parameters36B
Context4K
Layers48
Architecturellama
Smallest quant7.6 GB
Quick answer

Lumosia v2 MoE 4x10.7 i1 needs about 24.1 GB of memory at Q4_K_M (a 22.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 19 quants, from 7.6 GB (IQ1_S) to 29.8 GB (Q6_K).

Lumosia v2 MoE 4x10.7 i1 – 36B parameter mixture of experts

Lumosia v2 MoE 4x10.7 i1 is a 36B parameter model built on the llama architecture. It supports a 4096 token context window and is available in multiple GGUF quantizations. The model is released under the apache-2.0 license.

Good at

  • Large context handling
  • Mixture of experts for diverse tasks
  • Balanced performance across prompts

Limits

  • 4096 token context limit
  • Requires 8k context for memory estimates
  • No vision capabilities

Best for

  • Chat assistants needing 8k context
  • Research prototypes with limited GPU memory
  • Fine‑tuning on custom datasets

Who it’s for. Developers and researchers who need a large, versatile LLM that can be run locally with GGUF. The model is suitable for experimentation and production use where an 8k context window is sufficient.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.6 GB 8.9 GB
Too big Get file →
IQ2_XXS9.7 GB 11.0 GB
Too big Get file →
IQ2_XS10.8 GB 12.1 GB
Too big Get file →
IQ2_S11.0 GB 12.4 GB
Too big Get file →
IQ2_M12.1 GB 13.4 GB
Too big Get file →
Q2_K13.3 GB 14.6 GB
Too big Get file →
IQ3_XXS14.1 GB 15.4 GB
Too big Get file →
IQ3_XS14.8 GB 16.1 GB
Too big Get file →
Q3_K_S15.7 GB 17.0 GB
Too big Get file →
IQ3_S15.7 GB 17.1 GB
Too big Get file →
IQ3_M16.0 GB 17.3 GB
Too big Get file →
Q3_K_M17.4 GB 18.7 GB
Too big Get file →
Q3_K_L18.9 GB 20.2 GB
Too big Get file →
IQ4_XS19.4 GB 20.7 GB
Too big Get file →
Q4_K_S20.7 GB 22.0 GB
Too big Get file →
Q4_K_M22.0 GB 23.3 GB
Too big Get file →
Q5_K_S25.0 GB 26.3 GB
Too big Get file →
Q5_K_M25.8 GB 27.1 GB
Too big Get file →
Q6_K29.8 GB 31.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7.62 GB file, 9.7 GB memory). With 12 GB VRAM, IQ2_M (12.09 GB file, 14.2 GB memory) is a good balance. If 16 GB VRAM is available, Q3_K_M (17.44 GB file, 19.6 GB memory) offers higher quality.

What GPU do you need for Lumosia v2 MoE 4x10.7 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: 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: the best quant that fits is IQ2_XXS (9.7 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K (13.3 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_S (20.7 GB file, about 22.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (29.8 GB file, about 31.9 GB in use).

Which Lumosia v2 MoE 4x10.7 i1 quant should you choose?

Q4_K_M is the usual starting point for Lumosia v2 MoE 4x10.7 i1: it balances file size and quality well. Here it is a 22.0 GB file.

If memory is tight, the smallest file is IQ1_S at 7.6 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
Parameters36B (approximate, mixture of experts)
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilyLumosia
Licenseapache-2.0
Downloads (HF)1,006
Last updated2024-12-16

Frequently asked questions about Lumosia v2 MoE 4x10.7 i1

How much VRAM does Lumosia v2 MoE 4x10.7 i1 need?

About 24.1 GB at Q4_K_M with an 8K context window. That is the 22.0 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 Lumosia v2 MoE 4x10.7 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Lumosia v2 MoE 4x10.7 i1 GGUF?

It depends on the quant: IQ1_S is 7.6 GB, IQ2_XXS is 9.7 GB, IQ2_XS is 10.8 GB, IQ2_S is 11.0 GB, IQ2_M is 12.1 GB, Q2_K is 13.3 GB and 13 more.

What context length does Lumosia v2 MoE 4x10.7 i1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download Lumosia v2 MoE 4x10.7 i1 GGUF?

The files are on Hugging Face in the mradermacher/Lumosia-v2-MoE-4x10.7-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 Lumosia v2 MoE 4x10.7 i1 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 this model on 8 GB VRAM?

Yes, the IQ1_S quant uses 7.62 GB file size and requires about 9.7 GB memory at 8k context.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Lumosia-v2-MoE-4x10.7

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Lumosia models

All Lumosia →

Other large models

All large models →