Models

dlasher/Qwen3-VL-30B-A3B-Instruct-ENG

pulled as BF16, vocab slice (combined_en_huge) requant to IQ4_NL (combined_en_huge) -- (English + Coding focus) - ~20% faster than Q4_K_M

rbrisita/qwen3-coder

Qwen3 Coder 30B A3B Unsloth Dynamic 2.0 GGUF MoE

rbrisita/qwen3-coder-1m

Qwen3 Coder 30B A3B 1M Unsloth Dynamic 2.0 GGUF MoE

dlasher/Qwen3-VL-30B-A3B-Instruct

full BF16 model, hand-requant to IQ4_NL, with combined_en_huge dataset (English + Coding focus)

LoPld/qwen3-coder-30b-a3b-q4_K_S

Quantized Q4_K_S version of Qwen3-coder 30B FP16 model

qooba/qwen3-coder-30b-a3b-instruct

Qwen3-Coder-30B-A3B-Instruct-GGUF from: https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF

moophlo/Qwen3-Coder-30B-A3B-Instruct-GGUF

huihui_ai/qwenlong-l1.5-abliterated

QwenLong-L1.5, a long-context reasoning model built upon Qwen3-30B-A3B-Thinking, augmented with memory mechanisms to process tasks far beyond its physical context window.

fervent_mcclintock/Qwen3-Coder-30B-A3B-Instruct-Compliant

fervent_mcclintock/Qwen3-Coder-30B-A3B-Instruct-Pruned-15B-A3B

reaperdoesntrun/Qwen3-0.6B-Distilled

A 0.6B parameter model built in two stages: knowledge distillation from a 30B Thinking teacher to establish a structured reasoning backbone, then supervised fine-tuning on legal instruction data. 50x compression. Under 500MB quantized. Runs on a phone.

innocentevil0914/Qwen3-30B-A3B-Inst-unsloth-ud2-q8_k_xl

alibayram/Qwen3-30B-A3B-Instruct-2507

Qwen3-30B-A3B-Instruct-2507 has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 30.5B in total and 3.3B activated - Number of Paramaters (Non-Embedding): 29.9B - Number of Layers

mychen76/qwen3_cline_roocode

Quantized version of Qwen3 models (4B,8B,14B,32B, 30B-moe) optimized for tool usage in Cline / Roo Code and solving Complex Problems.

danielsheep/Qwen3-Coder-30B-A3B-Instruct-1M-Unsloth

Unsloth Dynamic 2.0 Quants achieves 1M tokens & superior accuracy & SOTA quantization performance. Select UD-IQ3_XXS for 16GB VRAM, UD-Q4_K_XL for 24GB VRAM, or UD-Q5_K_XL/UD-Q6_K_XL for 32GB VRAM.

SimonPu/Qwen3-Coder

Qwen3-Coder is available in multiple sizes. Today, we’re excited to introduce Qwen3-Coder-30B-A3B-Instruct. This streamlined model maintains impressive performance and efficiency ........

dengcao/Qwen3-30B-A3B-Instruct-2507

Qwen3-30B-A3B-Instruct-2507 has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 30.5B in total and 3.3B activated - Number of Paramaters (Non-Embedding): 29.9B - Number of Layers

ukjin/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill

This model is a distilled version of Qwen/Qwen3-30B-A3B-Instruct designed to inherit the reasoning and behavioral characteristics of its much larger teacher model, deepseek-ai/DeepSeek-V3.1.

anarko/qwen3-coder-flash

Unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF with defaults to consume roughly 32 GB of VRAM

mdq100/Qwen3-Coder-30B-A3B-Instruct

Qwen3-Coder is a highly capable coding assistant, based on Qwen3-Coder-30B-A3B-Instruct. She is designed for local development and agentic coding workflows