LU

Lumma fev 27B

LummaGGUF by FrontiersMindUpdated 2026-10-14
Download on Hugging Face
Parameters26.9B
Context256K
Layers64
Architectureqwen35
Smallest quant10.7 GB
Quick answer

Lumma fev 27B needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 7 quants, from 10.7 GB (Q2_K) to 53.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Lumma Fev 27B – a decision model for probability scoring

Lumma Fev 27B is a decision model based on Qwen3.8-27B. It receives a state and typed questions and returns a probability for each option in a single forward pass. The model never generates text and supports English, Hindi, Tamil and Kannada.

Good at

  • Probability scoring for multiple choice
  • Fast single‑pass inference
  • No text generation required

Limits

  • Requires 55 GB free VRAM for full model
  • Maximum context 8,192 tokens
  • No vision support in base model

Best for

  • Evaluating multiple‑choice exams
  • Automated decision support systems
  • Batch probability scoring

Who it’s for. Developers building decision‑making applications that need quick probability estimates without text generation. Suitable for educational assessment tools and automated QA systems.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.7 GB 13.4 GB
Too big Get file →
Q3_K_M13.3 GB 15.9 GB
Too big Get file →
Q4_K_M16.5 GB 19.2 GB
Too big Get file →
Q5_K_M19.2 GB 21.9 GB
Too big Get file →
Q6_K22.1 GB 24.7 GB
Too big Get file →
Q8_028.6 GB 31.2 GB
Too big Get file →
BF1653.8 GB 56.5 GB
Too big Get file →

For 8 GB VRAM use Q2_K (10.71 GB file, ~13.4 GB memory). For 16 GB VRAM use Q3_K_M (13.3 GB file, ~15.9 GB memory). For 24 GB VRAM use Q4_K_M (16.55 GB file, ~19.2 GB memory).

What GPU do you need for Lumma fev 27B?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q3_K_M (13.3 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).

Which Lumma fev 27B quant should you choose?

Q4_K_M is the usual starting point for Lumma fev 27B: it balances file size and quality well. Here it is a 16.5 GB file.

The Q8_0 file is 28.6 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 10.7 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

Architectureqwen35
Parameters26.9B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized byFrontiersMind
FamilyLumma
Licenseapache-2.0
Downloads (HF)653
Last updated2026-10-14

Frequently asked questions about Lumma fev 27B

How much VRAM does Lumma fev 27B need?

About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Lumma fev 27B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Lumma fev 27B GGUF?

It depends on the quant: Q2_K is 10.7 GB, Q3_K_M is 13.3 GB, Q4_K_M is 16.5 GB, Q5_K_M is 19.2 GB, Q6_K is 22.1 GB, Q8_0 is 28.6 GB and 1 more.

What context length does Lumma fev 27B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Lumma fev 27B GGUF?

The files are on Hugging Face in the FrontiersMind/Lumma-fev-27B-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 Lumma fev 27B 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 Lumma Fev 27B on 8 GB VRAM?

Yes, using the Q2_K quantization which requires about 13.4 GB of VRAM at 8,192 token context.

Does the model support image inputs?

Images can be passed via the lumma-fev[images] package, but the base model does not process vision data.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from FrontiersMind

All by FrontiersMind →

More Lumma models

All Lumma →

Other medium models

All medium models →