noctrex/Qwopus3.5-9B-Coder-MTPThese are quantizations of the model Jackrong / Qwopus3.5 9B Coder I've added the MTP layer on it. My personal speed improvement on my 7900XTX with the vulkan backend has been from ~80 tps to around ~120 tps. An imatrix has been calulated for coding tasks, as such it is specialized for coding. Quick Start 1. Download the latest release of llama.cpp . 2. Download your preferred model variant from below.

Qwopus3.5-9B-Coder-MTP

PUBLIC

Mirrored

These are quantizations of the model Jackrong / Qwopus3.5-9B-Coder

Tasks:image-text-to-text

imported

huggingface

minio

gguf

qwen

qwen3_5_moe

MTP

image-text-to-text

base_model:Jackrong/Qwopus3.5-9B-Coder

base_model:quantized:Jackrong/Qwopus3.5-9B-Coder

endpoints_compatible

region:us

imatrix

conversational

0downloads0likes

Model Card

Edit

These are quantizations of the model Jackrong / Qwopus3.5-9B-Coder
I've added the MTP layer on it.
My personal speed improvement on my 7900XTX with the vulkan backend has been from ~80 tps to around ~120 tps. An imatrix has been calulated for coding tasks, as such it is specialized for coding.

Quick Start

Download the latest release of llama.cpp.
Download your preferred model variant from below.

Inference Providers

This model isn't deployed by any Inference Provider yet. Deploy this model →

GGUF details

Format

GGUF

Model size

9B params

Architecture

Qwen

7 quantization variants

imatrix-code_micro4.9 MB

Qwopus3.5-9B-Coder-MTP-IQ3_XS4.4 GB

Qwopus3.5-9B-Coder-MTP-IQ3_M5.1 GB

Qwopus3.5-9B-Coder-MTP-IQ4_XS5.6 GB

Qwopus3.5-9B-Coder-MTP-Q4_K_XL5.8 GB

Qwopus3.5-9B-Coder-MTP-Q6_K7.1 GB

Qwopus3.5-9B-Coder-MTP-Q8_09.1 GB

Tasks

image-text-to-text

Source

Mirrored from an external registry.

Last synced 6/14/2026

Model tree for noctrex/Qwopus3.5-9B-Coder-MTP

Base model

Jackrong/Qwopus3.5-9B-Coder

Files

main

9 files · 37.1 GBHistory

Security scan in progress for 9 files.

main

9 files · 37.1 GB

.gitattributes2 KB

imatrix-code_micro.ggufLFS4.9 MB

Qwopus3.5-9B-Coder-MTP-IQ3_M.ggufLFS5.1 GB

Qwopus3.5-9B-Coder-MTP-IQ3_XS.ggufLFS4.4 GB

Qwopus3.5-9B-Coder-MTP-IQ4_XS.ggufLFS5.6 GB

Qwopus3.5-9B-Coder-MTP-Q4_K_XL.ggufLFS5.8 GB

Qwopus3.5-9B-Coder-MTP-Q6_K.ggufLFS7.1 GB

Qwopus3.5-9B-Coder-MTP-Q8_0.ggufLFS9.1 GB

README.md593 B

We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy