PU

PurpleMIST Flash 1.0

PurplemistGGUF by mradermacherUpdated 2026-10-14
Download on Hugging Face
Parameters7.94B
Context256K
Layers32
Architectureqwen35
Smallest quant3.5 GB
Quick answer

PurpleMIST Flash 1.0 needs about 6.6 GB of memory at Q4_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 3.5 GB (Q2_K) to 15.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

PurpleMIST Flash 1.0 – a 7.94B parameter decision model for calibrated probabilities

PurpleMIST Flash 1.0 is a 7.94B parameter decision model built on Qwen3.5-9B-Base. It scores options without generating text and is calibrated for African languages and English. The model is licensed under apache-2.0.

Good at

  • Calibrated probability scoring
  • Zero‑shot decision tasks
  • Supports African languages

Limits

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

Best for

  • Support ticket routing
  • Fraud detection in SMS
  • Multi‑option decision scoring

Who it’s for. Developers needing a lightweight decision engine that returns calibrated probabilities for multiple options. Ideal for applications that require fast, single‑pass scoring of unstructured state data.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.2 GB 5.8 GB
Fits Get file →
Q3_K_L4.5 GB 6.1 GB
Fits Get file →
IQ4_XS4.7 GB 6.3 GB
Fits Get file →
Q4_K_S4.8 GB 6.4 GB
Fits Get file →
Q4_K_M5.1 GB 6.6 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.8 GB 7.3 GB
Tight Get file →
Q6_K6.5 GB 8.1 GB
Too big Get file →
Q8_08.4 GB 10.0 GB
Too big Get file →
F1615.9 GB 17.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 4.78 GB, estimated 6.4 GB memory). For 16 GB VRAM, Q5_K_M (file size 5.77 GB, estimated 7.3 GB memory) offers a good balance. For larger budgets, Q8_0 (file size 8.45 GB, estimated 10 GB memory) provides full precision.

What GPU do you need for PurpleMIST Flash 1.0?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.2 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.8 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.4 GB file, about 10.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.4 GB file, about 10.0 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.9 GB file, about 17.5 GB in use).

Which PurpleMIST Flash 1.0 quant should you choose?

Q4_K_M is the usual starting point for PurpleMIST Flash 1.0: it balances file size and quality well. Here it is a 5.1 GB file.

The Q8_0 file is 8.4 GB, about 1.7 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 Q2_K at 3.5 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

Architectureqwen35
Parameters7.94B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)821
Last updated2026-10-14

Frequently asked questions about PurpleMIST Flash 1.0

How much VRAM does PurpleMIST Flash 1.0 need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 5.1 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 PurpleMIST Flash 1.0 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.8 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of PurpleMIST Flash 1.0 GGUF?

It depends on the quant: Q2_K is 3.5 GB, Q3_K_S is 3.8 GB, Q3_K_M is 4.2 GB, Q3_K_L is 4.5 GB, IQ4_XS is 4.7 GB, Q4_K_S is 4.8 GB and 6 more.

What context length does PurpleMIST Flash 1.0 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download PurpleMIST Flash 1.0 GGUF?

The files are on Hugging Face in the mradermacher/PurpleMIST-Flash-1.0-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 PurpleMIST Flash 1.0 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 PurpleMIST Flash 1.0 on 8 GB VRAM?

Yes, the Q4_K_S quant requires about 6.4 GB memory at 8k context, fitting within 8 GB VRAM.

Does the model support vision inputs?

No, PurpleMIST Flash 1.0 has the vision tower removed and only processes text.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Purplemist models

All Purplemist →

Other small models

All small models →