LE

Lev1 3.7B

LevGGUF by mradermacherUpdated 2026-10-14
Download on Hugging Face
Parameters5.06B
Context512K
Layers36
Architecturek2-horizon
Smallest quant2.1 GB
Quick answer

Lev1 3.7B needs about 4.9 GB of memory at Q4_K_M (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 2.1 GB (Q2_K) to 10.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Lev1 3.7B – a decision‑only LLM for structured input

Lev1 is a 5.06B‑parameter model that returns probabilities for structured questions. It never generates text and is optimized for fast inference. The model is released under Apache‑2.0.

Good at

  • Fast inference on structured queries
  • High decision‑index scores
  • Tool usage

Limits

  • No text generation
  • Limited to two question types
  • Requires 8k context for estimates

Best for

  • Decision‑making systems
  • Tool‑automation pipelines
  • Structured QA

Who it’s for. Developers building decision engines that need quick, probability‑based answers. The model is suitable for applications that require deterministic outputs without text generation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.1 GB 3.9 GB
Fits Get file →
Q3_K_S2.4 GB 4.1 GB
Fits Get file →
Q3_K_M2.6 GB 4.3 GB
Fits Get file →
Q3_K_L2.8 GB 4.5 GB
Fits Get file →
IQ4_XS2.9 GB 4.6 GB
Fits Get file →
Q4_K_S3.0 GB 4.7 GB
Fits Get file →
Q4_K_M3.2 GB 4.9 GB
Fits Get file →
Q5_K_S3.6 GB 5.3 GB
Fits Get file →
Q5_K_M3.6 GB 5.4 GB
Fits Get file →
Q6_K4.2 GB 5.9 GB
Fits Get file →
Q8_05.4 GB 7.1 GB
Fits Get file →
F1610.1 GB 11.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (3.16 GB file, ~4.9 GB memory). For 12 GB VRAM, Q5_K_M (3.64 GB file, ~5.4 GB memory) offers a balance of size and precision. Higher‑precision Q6_K or Q8_0 can be used if more VRAM is available.

What GPU do you need for Lev1 3.7B?

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 Q2_K (2.1 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (4.2 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.4 GB file, about 7.1 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (10.1 GB file, about 11.8 GB in use).

Which Lev1 3.7B quant should you choose?

Q4_K_M is the usual starting point for Lev1 3.7B: it balances file size and quality well. Here it is a 3.2 GB file.

The Q8_0 file is 5.4 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 2.1 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

Architecturek2-horizon
Parameters5.06B
Layers36
Trained context524,288 tokens
KV cache (fp16)144 KB per token

Source

Quantized bymradermacher
FamilyLev
Licenseapache-2.0
Downloads (HF)726
Last updated2026-10-14

Frequently asked questions about Lev1 3.7B

How much VRAM does Lev1 3.7B need?

About 4.9 GB at Q4_K_M with an 8K context window. That is the 3.2 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 Lev1 3.7B on an 8 GB GPU?

Yes, with Q8_0: the 5.4 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Lev1 3.7B GGUF?

It depends on the quant: Q2_K is 2.1 GB, Q3_K_S is 2.4 GB, Q3_K_M is 2.6 GB, Q3_K_L is 2.8 GB, IQ4_XS is 2.9 GB, Q4_K_S is 3.0 GB and 6 more.

What context length does Lev1 3.7B support?

The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Lev1 3.7B GGUF?

The files are on Hugging Face in the mradermacher/Lev1-3.7B-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 Lev1 3.7B 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 Lev1 on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 4.9 GB of VRAM at 8k context, which fits within an 8 GB budget.

Does Lev1 generate text?

No, Lev1 only returns probability scores for structured inputs and does not produce text.

What license does Lev1 use?

Lev1 is released under the Apache‑2.0 license.

Other GGUFs of Lev1-3.7B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Lev models

All Lev →

Other small models

All small models →