SofiTesfay2010
/

KAT-Coder-V3-Dev-Flash

imatrix-calibrated

Model card Files Files and versions

SofiTesfay2010/KAT-Coder-V3-Dev-Flash

Tencent STQ1_0 (Sherry 3:4) calibrated GGUF of Kwaipilot/KAT-Coder-V2.5-Dev.

Format: GGUF (type 42)
MoE Routing Experts: 1.3125 bpw (42 bytes / 256 weights)
Calibration Source: mradermacher/KAT-Coder-V2.5-Dev-i1-GGUF

Downloads last month: -

GGUF

Model size

35B params

Architecture

qwen2

Hardware compatibility

Log In to add your hardware

1-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for SofiTesfay2010/KAT-Coder-V3-Dev-Flash

Base model

Kwaipilot/KAT-Coder-V2.5-Dev

Quantized

(68)

this model