HO

Diplodocus preview 4

HorizonGGUF by OsaurusAIUpdated 2026-10-15
Download on Hugging Face
Parameters9B
Context512K
Layers36
Architecturek2-horizon
Smallest quant0.0 GB
Quick answer

Diplodocus preview 4 needs about 8.0 GB of memory at Q4_K_M (a 6.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 0.0 GB to 9.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Diplodocus preview 4 – a 9B‑parameter LLM for finance and document tasks

Diplodocus preview 4 is a 9‑billion‑parameter model built on IFM/K2-Horizon-7B. It supports reasoning and tool use, and is trained on finance, documents, spreadsheets and Osaurus workspace tools. The model is available in GGUF format for llama.cpp with K2‑Horizon support.

Good at

  • Reasoning with tools
  • Finance document processing
  • Spreadsheet calculations

Limits

  • Large context requires high VRAM
  • No vision support
  • Requires llama.cpp with K2‑Horizon support

Best for

  • Tool‑assisted finance queries
  • Automated spreadsheet editing
  • Document summarization

Who it’s for. Developers building finance or document assistants that need reasoning and tool integration. Users of llama.cpp who can compile the K2‑Horizon architecture. Those who prefer open‑source models under Apache‑2.0.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
Q4_K_M6.3 GB 8.0 GB
Too big Get file →
Q6_K7.8 GB 9.5 GB
Too big Get file →
Q8_09.6 GB 11.3 GB
Too big Get file →

For 8 GB VRAM, use the Q4_K_M quant (6.33 GB file, 8 GB memory at 8 k context). For 12 GB VRAM, Q6_K (7.76 GB file, 9.5 GB memory) is suitable. If you have 16 GB or more, Q8_0 (9.57 GB file, 11.3 GB memory) offers the highest fidelity. The unknown quant is only 0.01 GB but memory usage is not specified.

What GPU do you need for Diplodocus preview 4?

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 the main file (0.0 GB file, about 1.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (6.3 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.6 GB file, about 11.3 GB in use).

Which Diplodocus preview 4 quant should you choose?

Q4_K_M is the usual starting point for Diplodocus preview 4: it balances file size and quality well. Here it is a 6.3 GB file.

The Q8_0 file is 9.6 GB, about 1.5 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturek2-horizon
Parameters9B
Layers36
Trained context524,288 tokens
KV cache (fp16)144 KB per token

Source

Quantized byOsaurusAI
FamilyHorizon
Licenseapache-2.0
Downloads (HF)154,007
Last updated2026-10-15

Frequently asked questions about Diplodocus preview 4

How much VRAM does Diplodocus preview 4 need?

About 8.0 GB at Q4_K_M with an 8K context window. That is the 6.3 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 Diplodocus preview 4 on an 8 GB GPU?

Yes, with Q4_K_M: the 6.3 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Diplodocus preview 4 GGUF?

It depends on the quant: file is 0.0 GB, Q4_K_M is 6.3 GB, Q6_K is 7.8 GB, Q8_0 is 9.6 GB.

What context length does Diplodocus preview 4 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 Diplodocus preview 4 GGUF?

The files are on Hugging Face in the OsaurusAI/Diplodocus-preview-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 Diplodocus preview 4 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 Diplodocus preview 4 on 8 GB VRAM?

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

Does this model support image inputs?

No, Diplodocus preview 4 does not have vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of K2-Horizon-7B

Similar models

Browse all →

More from OsaurusAI

All by OsaurusAI →

More Horizon models

All Horizon →

Other small models

All small models →