Instructions to use lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test",
	filename="Qwen3.6-35B-A3B-DFlash-bf16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16
# Run inference directly in the terminal:
llama-cli -hf lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16
# Run inference directly in the terminal:
llama-cli -hf lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16
# Run inference directly in the terminal:
./llama-cli -hf lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16

Use Docker

docker model run hf.co/lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16

LM Studio
Jan
Ollama
How to use lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test with Ollama:
```
ollama run hf.co/lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16
```

Unsloth Studio

How to use lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test to start chatting

How to use lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16

Run Hermes

hermes

Docker Model Runner
How to use lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test with Docker Model Runner:
```
docker model run hf.co/lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16
```

Lemonade

How to use lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lym00/Qwen3.6-35B-A3B-DFlash-GGUF-Test:BF16

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-DFlash-GGUF-Test-BF16

List all available models

lemonade list

llama.cpp Pull Request: https://github.com/ggml-org/llama.cpp/pull/22105

DFlash Drafter: https://huggingface.co/z-lab/Qwen3.6-35B-A3B-DFlash

Steps (follow the PR)

git clone -b dflash https://github.com/ruixiang63/llama.cpp
download draft model from https://huggingface.co/z-lab/Qwen3.6-35B-A3B-DFlash/
download tokenizer from https://huggingface.co/Qwen/Qwen3.6-35B-A3B
convert draft model to gguf

python convert_hf_to_gguf.py ../Qwen3.6-35B-A3B-DFlash --outtype bf16 --target-model-dir ../Qwen3.6-35B-A3B --outfile ../Qwen3.6-35B-A3B-DFlash/Qwen3.6-35B-A3B-DFlash-bf16.gguf

Build llama.cpp

CUDA

cmake -B build -DGGML_CUDA=ON

cmake --build build --config Release -j

VULKAN

cmake -B build -DGGML_VULKAN=ON

cmake --build build --config Release -j

Run DFlash speculative decoding

# thinking off: set LLAMA_SPEC_NO_THINK=1
# Omit it to test thinking-mode behavior
export LLAMA_SPEC_NO_THINK=1

for prompt in \
    "Write a quicksort algorithm in Python. Write code only." \
    "Explain the Pythagorean theorem" \
    "Plan a 1 day trip to DC"; do
  echo "=== Prompt: $prompt ==="
  ./build/bin/llama-speculative-simple \
    -m  "${TARGET_MODEL_GGUF}" \
    -md "${DFLASH_MODEL_GGUF}" \
    --dflash -p "$prompt" -n 256 \
    --draft-max 16 \
    -cd 512 -c 1024 \
    --temp 0 --top-k 1 --seed 42 \
    -ngl 99 -ngld 99
done

Tests and Investigations

2026-04-19:

Rebase dflash feature onto latest master

git clone -b master https://github.com/ggml-org/llama.cpp
git remote add ruixiang63 https://github.com/ruixiang63/llama.cpp
git fetch ruixiang63
git checkout -b dflash-test origin/master
git merge ruixiang63/dflash --no-edit

Then solve conflicts manually

gguf-py/gguf/constants.py
src/CMakeLists.txt
src/llama-arch.cpp
src/llama-hparams.h
src/llama-model.cpp

Notes

src/CMakeLists.txt Use glob to collect src/models sources: https://github.com/ggml-org/llama.cpp/pull/22005/changes
src/llama-arch.cpp remove per-arch tensor name lists: https://github.com/ggml-org/llama.cpp/pull/21531/changes
src/llama-model.cpp Refactor bias tensor variable names: https://github.com/ggml-org/llama.cpp/pull/22079/changes#diff-36e262e316ec1404e29880eb8b8ce4660ac584f0d0434710efc48a66497bdb59

from:

layer.bq = create_tensor(tn(LLM_TENSOR_ATTN_Q,   "bias", i), {n_embd_head_k * n_head}, TENSOR_NOT_REQUIRED);
layer.bk = create_tensor(tn(LLM_TENSOR_ATTN_K,   "bias", i), {n_embd_k_gqa},          TENSOR_NOT_REQUIRED);
layer.bv = create_tensor(tn(LLM_TENSOR_ATTN_V,   "bias", i), {n_embd_v_gqa},          TENSOR_NOT_REQUIRED);
layer.bo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd},                TENSOR_NOT_REQUIRED);

to:

layer.wq_b = create_tensor(tn(LLM_TENSOR_ATTN_Q,   "bias", i), {n_embd_head_k * n_head}, TENSOR_NOT_REQUIRED);
layer.wk_b = create_tensor(tn(LLM_TENSOR_ATTN_K,   "bias", i), {n_embd_k_gqa},          TENSOR_NOT_REQUIRED);
layer.wv_b = create_tensor(tn(LLM_TENSOR_ATTN_V,   "bias", i), {n_embd_v_gqa},          TENSOR_NOT_REQUIRED);
layer.wo_b = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd},                TENSOR_NOT_REQUIRED);

src/models/dflash.cpp follows the same

layer.bq -> layer.wq_b

layer.bk -> layer.wk_b

layer.bv -> layer.wv_b

layer.bo -> layer.wo_b

src/models/eagle3.cpp:134: support NVFP4 tensors for Gemma4: https://github.com/ggml-org/llama.cpp/pull/21971/changes#diff-9be9eea14f4aefce7375482c05968900192634e88e92ac263cedb955a64ad7feR2099

        cur = build_attn(inp_attn,
                model.layers[il].wo, NULL, NULL, // 3rd tensor parameter (wo_s)
                Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il);

2026-04-20:

Support for Qwen3.5/3.6 MoE and notes

Z Lab's new benchmark

https://huggingface.co/z-lab/Qwen3.6-35B-A3B-DFlash/commit/82252400cd9baebdfa5730b0aa809e10db5dba12

2026-04-22:

Re-uploaded gguf based on new drafter https://huggingface.co/z-lab/Qwen3.6-35B-A3B-DFlash/commit/31977fbe13a86e8b961774f773058175676d89b8

Issues and Solutions

/src/models/dflash.cpp:39: GGML_ASSERT(model.target_tok_embd != nullptr && "DFlash decoder requires target model's tok_embd") failed

check if --dflash param is added to the llama-speculative-simple test

Downloads last month: 581

GGUF

Model size

0.5B params

Architecture

dflash

Hardware compatibility

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support