FreedomAISVR/Qwen3.6-35B-A3B-Claude-4.7-Distill-MXFP4-MOE-GGUF overview
license: apache 2.0 tags: qwen3 qwen3.5 moe mixture of experts claude distillation mxfp4 mxfp4 moe gguf text generation pipeline tag: text generation Qwen3.6 3…
Runs locally from ~18.87 GB disk (24 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| qwen36-35b-distill-mxfp4_moe.gguf | GGUF | GGUF | 18.87 GB | Download |
Model Details
| Model ID | FreedomAISVR/Qwen3.6-35B-A3B-Claude-4.7-Distill-MXFP4-MOE-GGUF |
|---|---|
| Author | FreedomAISVR |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | — |
| Last modified | 2026-06-18T04:38:04.000Z |
Model README
---
license: apache-2.0
tags:
- qwen3
- qwen3.5
- moe
- mixture-of-experts
- claude
- distillation
- mxfp4
- mxfp4_moe
- gguf
- text-generation
pipeline_tag: text-generation
---
Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled MXFP4 MoE GGUF
GGUF quantization of lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled — a 35B MoE (3B active) reasoning model distilled from Claude 4.7 Opus.
Model Details
- Architecture: Qwen3.5 MoE, 41 blocks (40 layers + 1 MTP head), 256 experts (8 active/token)
- Active Parameters: ~3B
- Context: 262,144 tokens
- Source: Apache 2.0 license
- Text-only: No vision support
Quantization
| File | Type | Size | BPW |
|------|------|------|-----|
| qwen36-35b-distill-mxfp4_moe.gguf | MXFP4 (experts) + Q8_0 (non-experts) | ~18.87 GB | 4.56 |
MoE expert weights quantized to MXFP4. Non-expert weights (attention, shared experts, norms) quantized to Q8_0. Router weights kept at F32.
Usage
./llama-server -m qwen36-35b-distill-mxfp4_moe.gguf --host 0.0.0.0 --port 8080Credits
- Original model: lordx64
- Quantization: FreedomAISVR
Run FreedomAISVR/Qwen3.6-35B-A3B-Claude-4.7-Distill-MXFP4-MOE-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models