This is a derivative of Qwen3.6-35B-A3B. All credit for the base model architecture and weights goes to the original authors. The base model's license applies to this derivative.

Quantization Method

Quantized using MagicQuant hybrid evolutionary per-tensor quantization, based on the methodology by magiccodingman:

Tensors are classified into sensitivity groups (Embeddings, Head, Query, Key, Output, FFN Up/Down, MoE Experts, Router)
An evolutionary search finds the optimal quantization type per group, balancing size vs. perplexity
Q4/Q5/Q6 tier targets are produced with different size-quality tradeoffs
Small-row tensors and sensitivity-critical layers (embeddings, output head, router) are kept at F32/F16/BF16
This is NOT a uniform quantization -- each tensor group gets its own optimal type

GGUF Files

File	Size	Quant
Qwen3.6-35B-A3B-Q4_K_M.gguf	21.7 GB	Q4 hybrid
Qwen3.6-35B-A3B-Q5_K_M.gguf	25.4 GB	Q5 hybrid
Qwen3.6-35B-A3B-Q6_K.gguf	29.1 GB	Q6 hybrid

Usage

LM Studio

Download the GGUF file of your preferred quantization tier
Place it in your LM Studio models directory
Load the model in LM Studio -- it will auto-detect the chat template
The model supports the base model's full context length

llama.cpp

bash

# Interactive chat (--jinja uses the model's embedded chat template, not a hardcoded one)
llama-cli -m Qwen3.6-35B-A3B-Q5_K_M.gguf -c 8192 --jinja -cnv

# Single prompt
llama-cli -m Qwen3.6-35B-A3B-Q5_K_M.gguf -c 8192 -p "Your prompt here"

# Server mode
llama-server -m Qwen3.6-35B-A3B-Q5_K_M.gguf -c 8192 --port 8080 --jinja

Python (llama-cpp-python)

python

from llama_cpp import Llama

llm = Llama(model_path="./Qwen3.6-35B-A3B-Q5_K_M.gguf", n_ctx=8192)
output = llm.create_chat_completion(
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)
print(output["choices"][0]["message"]["content"])

Serving: MTP Speculative Decoding

This model includes MTP ("nextn") draft tensors, enabling self-speculative decoding -- measured ~1.6-1.9x faster generation with a ~95% first-token accept rate (no separate draft model needed; it drafts from itself):

llama-server -m Qwen3.6-35B-A3B-Q4_K_M.gguf -c 8192 --port 8080 --host 127.0.0.1 -ngl 99 -md Qwen3.6-35B-A3B-Q4_K_M.gguf --spec-type draft-mtp -ctk q8_0 -ctv q8_0 -fa on

Memory cost: MTP needs its own draft context alongside the main context, so serving with it uses roughly 2x the model's memory compared to serving without -md/--spec-type draft-mtp.

Caveats

The base model's license (apache-2.0) applies to all derivative files
Quantization reduces precision -- verify outputs for your specific use case
The hybrid quantization assigns different precision to different tensor groups, which means quality characteristics may differ from uniform quantizations

Limitations

Quantized models may exhibit subtle differences from the full-precision fine-tune
This model inherits any limitations and biases present in the base model

Generated with MagicQuant

lmcoleman/Qwen3.6-35B-A3B-MagicQuant-GGUF

Qwen3.6-35B-A3B-MagicQuant-GGUF

Base Model