Qwythos GGUF models

125 GGUF models in the Qwythos family, quantized by 100 uploaders. Sizes run from 1M to 71.8B parameters. The longest trained context is 1024K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
QW
Qwythos-9B-v2
Qwythos · empero-ai
Params8.95B
Context1024K
Q4_K_M5.7 GB
ReasoningTool useVision
QW
Qwythos 9B Claude Mythos 5 1M
Qwythos · empero-ai
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Qwythos-27B
Qwythos · empero-ai
Params27B
Context1024K
Q4_K_M17.3 GB
ReasoningVision
QW
Huihui Qwythos 9B Claude Mythos 5 1M Abliterated MTP
Qwythos · huihui-ai
Params9.2B
Context1024K
Smallest5.8 GB
ReasoningTool useVision
QW
Qwythos 9B Claude Mythos 5 1M Uncensored Heretic
Qwythos · llmfan46
Params8.95B
Context1024K
Q4_K_M6.2 GB
ReasoningTool useVision
QW
Qwythos 9B v2
Qwythos · bartowski
Params9.2B
Context1024K
Q4_K_M6.0 GB
Reasoning
QW
Qwythos 9B v2
Qwythos · mradermacher
Params9.2B
Context1024K
Q4_K_M5.8 GB
ReasoningVision
QW
Qwythos 9B v2
Qwythos · mradermacher
Params9.2B
Context1024K
Q4_K_M5.8 GB
Reasoning
QW
Qwythos 9B v2 Heretic
Qwythos · WaveCut
Params8.95B
Context1024K
Q4_K_M5.6 GB
GGUF
QW
Qwythos 9B Claude Mythos Uncensored Abliterated 1M
Qwythos · mradermacher
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool use
QW
Qwythos 9B Claude Mythos 5 1M MTP
Qwythos · mradermacher
Params9.2B
Context1024K
Q4_K_M5.8 GB
ReasoningTool useVision
QW
Qwythos 27B v1
Qwythos · mradermacher
Params27.3B
Context1024K
Q4_K_M16.8 GB
ReasoningTool useVision
QW
Qwythos 9B Claude Mythos 5 1M
Qwythos · N8STORM
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Qwythos 9B Claude Mythos 5 1M
Qwythos · Zaidusht
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Qwythos 9b Openthoughts
Qwythos · mradermacher
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool use
QW
Qwythos 27B v1
Qwythos · mradermacher
Params27.3B
Context1024K
Q4_K_M16.8 GB
ReasoningTool useVision
QW
Qwythos 9B Claude Mythos 5 1M MTP
Qwythos · wepiqx
Params9.2B
Context1024K
Smallest6.3 GB
ReasoningTool useVision
QW
Qwythos 9B Claude Mythos Uncensored Abliterated 1M
Qwythos · mradermacher
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool use
QW
Qwythos 9B v2 Heretic Abliterated
Qwythos · maxylium
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool use
QW
Qwythos 9B Cyber M1 Manager
Qwythos · mradermacher
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool use
QW
Qwythos-27B
Qwythos · Fastiraz
Params26.9B
Context1024K
Q4_K_M17.3 GB
ReasoningTool useVision
QW
Qwythos 9B Claude Mythos 5 1M
Qwythos · Supbatomic
Params9B
Context—
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Qwythos 9B Claude Mythos 5 1M MTP
Qwythos · mradermacher
Params9.2B
Context1024K
Q4_K_M5.8 GB
ReasoningTool use
QW
Qwythos 9B Claude Mythos 5 1M
Qwythos · Coding123defy
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Qwythos 9B Claude Mythos 5 1M
Qwythos · developerjeremylive
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Qwythos 9B Claude Mythos 5 1M
Qwythos · chiakelvin
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
CobrIX 1.0 Coder Full 72B A18B
Qwythos · CobrIX
Params71.8B
Context1024K
Q4_K_M43.7 GB
Coding
QW
Qwythos 9B Claude Mythos 5 1M
Qwythos · ApertureQA
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Qwythos 9B Claude Mythos 5 1M
Qwythos · ArkhAngelLifeJiggy
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Qwythos 9B Claude Mythos 5 1M
Qwythos · hackoffice
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool useVision

About the Qwythos GGUF models

Qwythos is represented on ggufmodels.com by 125 GGUF models, quantized by 100 uploaders on Hugging Face. The most downloaded are Qwythos-9B-v2, Qwythos 9B Claude Mythos 5 1M and Qwythos-27B. Parameter counts run from 1M to 71.8B, and the longest trained context window is 1024K tokens.

A Q4_K_M file of a Qwythos model is between 5.6 to 43.7 GB, which is the quant most people start with. Most files come from mradermacher (11), empero-ai (3) and developerjeremylive (3). The quants you will meet most often are Q5_K_M (102), Q4_K_M (102), Q8_0 (100) and Q6_K (98), where the number is how many models offer that quant.

Frequently asked questions

Which Qwythos GGUF should I download?

The most downloaded Qwythos GGUF here is Qwythos-9B-v2. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Qwythos model need?

Q4_K_M files of Qwythos models on this site range from 5.6 to 43.7 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Qwythos GGUF files come from?

The most common quantizers here are mradermacher, empero-ai and developerjeremylive. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing