CY

Cypher CoT 1.8B i1

CypherGGUF by mradermacherUpdated 2024-12-12
Download on Hugging Face
Parameters1.83B
Context16K
Layers24
Architecturellama
Smallest quant0.4 GB
Quick answer

Cypher CoT 1.8B i1 needs about 2.1 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.4 GB (IQ1_S) to 1.5 GB (Q6_K).

Cypher CoT 1.8B i1 – a 1.83B parameter Llama model fine‑tuned for chain‑of‑thought tasks

Cypher CoT 1.8B i1 is a 1.83B parameter Llama model fine‑tuned on a variety of CoT tasks. It supports up to 16384 context tokens and is released under the apache-2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Chain‑of‑thought reasoning
  • Coding assistance
  • Short‑form dialogue

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • No mixture‑of‑experts

Best for

  • Debugging code snippets
  • Explaining algorithm steps
  • Generating step‑by‑step solutions

Who it’s for. Developers and researchers who need a lightweight Llama model for CoT tasks. The model is suitable for local deployment on machines with limited VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.4 GB 1.4 GB
Fits Get file →
IQ1_M0.5 GB 1.5 GB
Fits Get file →
IQ2_XXS0.5 GB 1.5 GB
Fits Get file →
IQ2_XS0.6 GB 1.6 GB
Fits Get file →
IQ2_S0.6 GB 1.6 GB
Fits Get file →
IQ2_M0.7 GB 1.7 GB
Fits Get file →
Q2_K_S0.7 GB 1.7 GB
Fits Get file →
Q2_K0.7 GB 1.7 GB
Fits Get file →
IQ3_XXS0.7 GB 1.7 GB
Fits Get file →
IQ3_XS0.8 GB 1.8 GB
Fits Get file →
Q3_K_S0.8 GB 1.8 GB
Fits Get file →
IQ3_S0.8 GB 1.8 GB
Fits Get file →
IQ3_M0.9 GB 1.9 GB
Fits Get file →
Q3_K_M0.9 GB 1.9 GB
Fits Get file →
Q3_K_L1.0 GB 2.0 GB
Fits Get file →
IQ4_XS1.0 GB 2.0 GB
Fits Get file →
Q4_01.1 GB 2.1 GB
Fits Get file →
Q4_K_S1.1 GB 2.1 GB
Fits Get file →
Q4_K_M1.1 GB 2.1 GB
Fits Get file →
Q5_K_S1.3 GB 2.3 GB
Fits Get file →
Q5_K_M1.3 GB 2.3 GB
Fits Get file →
Q6_K1.5 GB 2.5 GB
Fits Get file →

For 8‑GB VRAM, use IQ1_S (0.44 GB, 1.4 GB memory) or IQ1_M (0.47 GB, 1.5 GB memory). If 12‑GB VRAM is available, Q3_K_M (0.91 GB, 1.9 GB memory) or Q4_K_M (1.11 GB, 2.1 GB memory) provide better quality. Higher quants such as Q6_K (1.5 GB, 2.5 GB memory) require more VRAM but offer the best fidelity.

What GPU do you need for Cypher CoT 1.8B 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 Q6_K (1.5 GB file, about 2.5 GB in use).

Which Cypher CoT 1.8B i1 quant should you choose?

Q4_K_M is the usual starting point for Cypher CoT 1.8B i1: it balances file size and quality well. Here it is a 1.1 GB file.

If memory is tight, the smallest file is IQ1_S at 0.4 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
Parameters1.83B
Layers24
Trained context16,384 tokens
KV cache (fp16)60 KB per token

Source

Quantized bymradermacher
FamilyCypher
Licenseapache-2.0
Downloads (HF)1,217
Last updated2024-12-12

Frequently asked questions about Cypher CoT 1.8B i1

How much VRAM does Cypher CoT 1.8B i1 need?

About 2.1 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Cypher CoT 1.8B i1 on an 8 GB GPU?

Yes, with Q6_K: the 1.5 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Cypher CoT 1.8B i1 GGUF?

It depends on the quant: IQ1_S is 0.4 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.5 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.6 GB, IQ2_M is 0.7 GB and 16 more.

What context length does Cypher CoT 1.8B i1 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.0 GB at 16K.

Where can I download Cypher CoT 1.8B i1 GGUF?

The files are on Hugging Face in the mradermacher/Cypher-CoT-1.8B-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 Cypher CoT 1.8B 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 Cypher CoT 1.8B i1 on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations; they require about 1.4–1.5 GB VRAM at 8‑k context.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Cypher-CoT-1.8B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Cypher models

All Cypher →

Other tiny models

All tiny models →