selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

Oomni logo

Can the RTX 4060 run mithi-v1-flash?

mithi-v1-flash·99M·GeForce RTX 4060·8 GB VRAM

Saved in this browser, used on every model page.
Yes

Yes. The RTX 4060 runs mithi-v1-flash fully in VRAM at FP16 / BF16 (about 0.7 GB of 8.0 GB).

best quant
FP16 / BF16
needs
0.7 GB
usable
8.0 GB

Estimates from the model's size.Try other contexts on the mithi-v1-flash page →

Every quantisation of mithi-v1-flash on the RTX 4060

QuantMemoryFit
Q4_K_M 0.6 GBfits
Q8_0 0.6 GBfits
FP16 / BF16 pick0.7 GBfits

Speed is a bandwidth-based estimate for generating text (272 GB/s); prompt processing and long contexts are slower.

TTS models that fit the RTX 4060 comfortably

All that fit →
ModelParamsBest quantMemoryLicence
hexgrad logoKokoro-82Mhexgrad
82MFP16 / BF16≈0.7 GBFits in memoryCommercial OK
OpenMOSS-Team logoMOSS-TTS-Nano-100MOpenMOSS-Team
100MFP16 / BF16≈0.7 GBFits in memoryCommercial OK
82MFP16 / BF16≈0.7 GBFits in memoryCommercial OK
Supertone logosupertonic-2Supertone
66MFP16 / BF16≈0.7 GBFits in memoryConditions
Supertone logosupertonicSupertone
66MFP16 / BF16≈0.7 GBFits in memoryConditions
170MFP16 / BF16≈0.9 GBFits in memoryConditions

Other GPUs that run mithi-v1-flash

Frequently asked questions

Can the RTX 4060 run mithi-v1-flash?
Yes. The RTX 4060 runs mithi-v1-flash fully in VRAM at FP16 / BF16 (about 0.7 GB of 8.0 GB).
Which quantisation of mithi-v1-flash should I use on the RTX 4060?
FP16 / BF16: the largest one that fits. Expected quality: lossless compared with the full-precision weights.

Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.