QW

speakoflow mini

QwenGGUF by SpeakoFlowUpdated 2026-08-29
Download on Hugging Face
Parameters773M
Context256K
Layers25
Architectureqwen35
Smallest quant0.5 GB
Quick answer

speakoflow mini needs about 1.5 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.5 GB (Q4_K_M) to 1.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.

Speakoflow Mini 0.8B – a lightweight dictation cleanup model

Speakoflow Mini is a 0.773 billion‑parameter causal language model fine‑tuned from Qwen3.5‑0.8B for speech transcription cleanup. It removes filler words, corrects punctuation and capitalization while preserving the speaker’s intent. The model is available in GGUF format and runs on CPU via llama.cpp.

Good at

  • Speech transcription cleanup
  • Punctuation and capitalization correction
  • Preserving speaker intent

Limits

  • No vision support
  • Not a chat or rewriter model
  • Requires 8 k context for full performance

Best for

  • Offline dictation cleanup on Windows, macOS, Linux
  • Post‑processing of transcribed speech
  • Voice assistant text refinement

Who it’s for. Developers building offline voice assistants or transcription pipelines who need deterministic cleanup of spoken text. The model is suitable for research and prototyping of dictation‑cleanup workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.5 GB 1.5 GB
Fits Get file →
Q5_K_M0.6 GB 1.5 GB
Fits Get file →
Q6_K0.6 GB 1.6 GB
Fits Get file →
Q8_00.8 GB 1.8 GB
Fits Get file →
BF161.6 GB 2.5 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M or Q5_K_M (≈0.54–0.59 GB) are recommended, using about 1.5 GB of VRAM at 8 k context. If more VRAM is available, Q6_K or Q8_0 offer higher precision. BF16 requires ~1.56 GB file size and ~2.5 GB VRAM.

What GPU do you need for speakoflow mini?

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 BF16 (1.6 GB file, about 2.5 GB in use).

Which speakoflow mini quant should you choose?

Q4_K_M is the usual starting point for speakoflow mini: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.8 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters773M
Layers25
Trained context262,144 tokens
KV cache (fp16)50 KB per token

Source

Quantized bySpeakoFlow
FamilyQwen
Licenseapache-2.0
Downloads (HF)15,525
Last updated2026-08-29

Frequently asked questions about speakoflow mini

How much VRAM does speakoflow mini need?

About 1.5 GB at Q4_K_M with an 8K context window. That is the 0.5 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 speakoflow mini on an 8 GB GPU?

Yes, with BF16: the 1.6 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 speakoflow mini GGUF?

It depends on the quant: Q4_K_M is 0.5 GB, Q5_K_M is 0.6 GB, Q6_K is 0.6 GB, Q8_0 is 0.8 GB, BF16 is 1.6 GB.

What context length does speakoflow mini support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.

Where can I download speakoflow mini GGUF?

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

What license does speakoflow mini 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 Speakoflow Mini on 8 GB VRAM?

Yes, the Q4_K_M or Q5_K_M quantizations fit within 8 GB VRAM, using about 1.5 GB at 8 k context.

Does this model support vision input?

No, Speakoflow Mini is a text‑only causal language model and does not process visual data.

Is the model licensed for commercial use?

The model is released under the Apache‑2.0 license, allowing commercial deployment.

Other GGUFs of Qwen3.5-0.8B

Similar models

Browse all →

More Qwen models

All Qwen →

Other tiny models

All tiny models →