Downloads · 30 days
73
9% of all-time downloads
Qwen3-6-KMP-Dev-GGUF
siendsi/Qwen3-6-KMP-Dev-GGUF
Qwen3-6-KMP-Dev-GGUF is a text generation model from siendsi. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as apache-2.0.
A pruned Qwen3.6-35B-A3B model optimized for Kotlin Multiplatform development and agentic tool use.
All-time downloads
831
Public
Repo size
33.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf23.7 GB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- License
- apache-2.0
- Access
- Public
- Created
- Aug 11, 2026
- Updated
- Aug 13, 2026
- SHA
- 95a3fdbd
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.6-35B-A3B KMP Dev (pruned)
A pruned Qwen3.6-35B-A3B model optimized for Kotlin Multiplatform development and agentic tool use.
License: Apache 2.0. Based on Qwen3.6-35B-A3B by Alibaba Cloud (Apache 2.0). Modified via expert pruning.
What's kept
- Kotlin, Swift, Gradle, Coroutines, RxSwift, Jetpack Compose, Compose Multiplatform, SwiftUI, Decompose, Metro, Koin, Ktor, Room, Coil
- English and Russian
- Reasoning, instruction following, tool use / function calling
- General knowledge (humanities)
What's removed
- Other programming languages (Python, Java, Go, Rust, C, JS, PHP, Ruby, TS, HTML, bash, Qt)
- Science/tech/esoteric domains (medicine, law, biology, chemistry, astronomy, physics, esoterics, cooking, dietetics)
- All languages except English and Russian
Pruning method
- Smart pruning: kept top-150 most active experts per layer (out of 256) based on heat data
- Calibrated on 36 texts × 3 runs (Kotlin, Swift, RU/EN, SQL, architecture, reasoning, tool use, JSON/API) — 100% deterministic
- Experts that don't activate on keep-texts are physically removed
- Quantization: Q3_K_M (9.7GB)
Variants
| Variant | Format | Size | Quality |
|---|---|---|---|
| GGUF Q3_K_M | GGUF | 9.7GB | ~90% of original |
| GGUF Q2_K | GGUF | 7.6GB | ~75% of original |
| GGUF IQ1_M | GGUF | 4.9GB | ~60% of original, loops on tool use |
| MLX 2-bit | safetensors | 6.3GB | ~75% of original |
Usage
- LM Studio:
lms get siendsi/qwen3-6-kmp-dev - llama.cpp:
llama-server -m Qwen3.6-35B-A3B-UD-Q3_K_M.gguf -c 16384 - MLX:
mlx_lm.generate --model siendsi/Qwen3-6-KMP-Dev-MLX-4bit
Architecture
- 40 layers, hybrid: attention (every 4th) + SSM (Gated DeltaNet) + MoE
- 150 experts/layer, 8 active, 1 shared
- embedding 2048, 16 heads, 2 KV heads, head_dim 256
- rope dim 64, mrope [11,11,10,0], freq_base 10M
- Task
- Text Generation
- Library
- gguf
- License
- apache-2.0
- Created
- Aug 11, 2026
- Updated
- Aug 13, 2026