SP

rizzo flow

SparkGGUF by rizzoaiacademyUpdated 2026-09-25
Download on Hugging Face
Parameters1.71B
Context1024K
Layers36
Architecturespark2_5
Smallest quant1.8 GB
Quick answer

rizzo flow needs about 4.3 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 1.8 GB (Q8_0) to 8.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Rizzo Flow: Spark-X2.5 LoRA fine‑tune for typed decision outputs

Rizzo Flow is a LoRA fine‑tune of Spark‑X2.5-1.7B and Spark‑X2.5-4B. It generates no text; instead it outputs probabilities for typed decisions (boolean, choice, score). The model runs a single forward pass per question.

Good at

  • Typed decision generation
  • Single‑pass inference
  • No text output

Limits

  • No vision support
  • Requires 1M‑token context
  • Apache‑2.0 license

Best for

  • Decision‑making systems
  • Agent workflows
  • Probability‑based interfaces

Who it’s for. Developers building agentic or decision‑making applications that need fast, single‑pass inference without text generation. The model is suitable for environments where only probability outputs are required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_01.8 GB 3.5 GB
Fits Get file →
Q4_K_M2.6 GB 4.3 GB
Fits Get file →
BF163.4 GB 5.1 GB
Fits Get file →
Q8_04.4 GB 6.1 GB
Fits Get file →
BF168.2 GB 9.9 GB
Too big Get file →

For 8 GB VRAM, use the Q8_0 quant (1.82 GB file, ~3.5 GB memory at 8 k context). For 4 GB VRAM, use Q4_K_M (2.6 GB file, ~4.3 GB memory). Larger VRAM allows BF16 (3.42 GB file, ~5.1 GB memory).

What GPU do you need for rizzo flow?

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 Q8_0 (1.8 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (3.4 GB file, about 5.1 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.4 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.2 GB file, about 9.9 GB in use).

Which rizzo flow quant should you choose?

Q4_K_M is the usual starting point for rizzo flow: it balances file size and quality well. Here it is a 2.6 GB file.

The Q8_0 file is 1.8 GB, about 0.7 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 Q8_0 at 1.8 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturespark2_5
Parameters1.71B
Layers36
Trained context1,048,576 tokens
KV cache (fp16)144 KB per token

Source

Quantized byrizzoaiacademy
FamilySpark
Licenseapache-2.0
Downloads (HF)7,125
Last updated2026-09-25

Frequently asked questions about rizzo flow

How much VRAM does rizzo flow need?

About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.6 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 rizzo flow on an 8 GB GPU?

Yes, with Q8_0: the 4.4 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of rizzo flow GGUF?

It depends on the quant: Q8_0 is 1.8 GB, Q4_K_M is 2.6 GB, BF16 is 3.4 GB, Q8_0 is 4.4 GB, BF16 is 8.2 GB.

What context length does rizzo flow support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). 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 rizzo flow GGUF?

The files are on Hugging Face in the rizzoaiacademy/rizzo-flow repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does rizzo flow 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 Rizzo Flow on 8 GB VRAM?

Yes, the Q8_0 quant file is 1.82 GB and requires about 3.5 GB of VRAM at 8 k context.

Does Rizzo Flow support image inputs?

No, the model does not have vision capabilities.

Other GGUFs of Spark-X2.5-1.7B

Similar models

Browse all →

More from rizzoaiacademy

All by rizzoaiacademy →

More Spark models

All Spark →

Other tiny models

All tiny models →