KH

kheops compressed

KheopsGGUF by mradermacherUpdated 2024-09-17
Download on Hugging Face
Parameters283M
Context2K
Layers3
Architecturellama
Smallest quant0.1 GB
Quick answer

kheops compressed needs about 0.9 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.1 GB (Q2_K) to 0.6 GB (F16).

kheops compressed – a 0.283B llama-based GGUF model

kheops compressed is a 0.283B parameter llama architecture model. It is available in multiple static quantizations and supports 2048 token context. The model is released under the apache-2.0 license.

Good at

  • Compact size for low‑memory setups
  • Fast inference with small context
  • Stable performance across quant types

Limits

  • No vision support
  • Limited to 2048 token context
  • Requires at least 0.8 GB VRAM for Q2_K

Best for

  • Embedded inference on edge devices
  • Rapid prototyping with low VRAM
  • Testing quantization effects

Who it’s for. Developers needing a lightweight llama model for local deployment. Researchers exploring quantization trade‑offs on small hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 0.7 GB
Fits Get file →
IQ3_XS0.1 GB 0.7 GB
Fits Get file →
IQ3_S0.2 GB 0.7 GB
Fits Get file →
Q3_K_S0.2 GB 0.7 GB
Fits Get file →
IQ3_M0.2 GB 0.7 GB
Fits Get file →
Q3_K_M0.2 GB 0.7 GB
Fits Get file →
Q3_K_L0.2 GB 0.7 GB
Fits Get file →
IQ4_XS0.2 GB 0.7 GB
Fits Get file →
Q4_K_S0.2 GB 0.7 GB
Fits Get file →
Q4_K_M0.2 GB 0.7 GB
Fits Get file →
Q5_K_S0.2 GB 0.8 GB
Fits Get file →
Q5_K_M0.2 GB 0.8 GB
Fits Get file →
Q6_K0.2 GB 0.8 GB
Fits Get file →
Q8_00.3 GB 0.9 GB
Fits Get file →
F160.6 GB 1.1 GB
Fits Get file →

For 8 GB VRAM, Q2_K (0.14 GB, 0.8 GB memory) or IQ3_XS (0.15 GB, 0.9 GB memory) are suitable. If 16 GB VRAM is available, Q4_K_M (0.19 GB, 0.9 GB memory) or Q5_K_M (0.21 GB, 0.9 GB memory) provide better quality. For the highest quality within 32 GB VRAM, use Q8_0 (0.3 GB, 1 GB memory) or F16 (0.57 GB, 1.3 GB memory).

What GPU do you need for kheops compressed?

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 F16 (0.6 GB file, about 1.3 GB in use).

Which kheops compressed quant should you choose?

Q4_K_M is the usual starting point for kheops compressed: it balances file size and quality well. Here it is a 0.2 GB file.

The Q8_0 file is 0.3 GB, about 1.6 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 0.1 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

Architecturellama
Parameters283M
Layers3
Trained context2,048 tokens
KV cache (fp16)24 KB per token

Source

Quantized bymradermacher
FamilyKheops
Licenseapache-2.0
Downloads (HF)1,738
Last updated2024-09-17

Frequently asked questions about kheops compressed

How much VRAM does kheops compressed need?

About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.2 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 kheops compressed on an 8 GB GPU?

Yes, with F16: the 0.6 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of kheops compressed GGUF?

It depends on the quant: Q2_K is 0.1 GB, IQ3_XS is 0.1 GB, IQ3_S is 0.2 GB, Q3_K_S is 0.2 GB, IQ3_M is 0.2 GB, Q3_K_M is 0.2 GB and 9 more.

What context length does kheops compressed support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.1 GB at 2K.

Where can I download kheops compressed GGUF?

The files are on Hugging Face in the mradermacher/kheops_compressed-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 kheops compressed 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 kheops compressed on 8 GB VRAM?

Yes, Q2_K or IQ3_XS quantizations fit within 8 GB VRAM with 0.8–0.9 GB memory usage at 8k context.

Does the model support vision tasks?

No, kheops compressed is a text‑only model with no vision capabilities.

What license does the model use?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other tiny models

All tiny models →