Instructions to use AesSedai/Qwen3.5-35B-A3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use AesSedai/Qwen3.5-35B-A3B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M

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 AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M

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 AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use AesSedai/Qwen3.5-35B-A3B-GGUF with Ollama:
```
ollama run hf.co/AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M
```

Unsloth Studio

How to use AesSedai/Qwen3.5-35B-A3B-GGUF 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 AesSedai/Qwen3.5-35B-A3B-GGUF 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 AesSedai/Qwen3.5-35B-A3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AesSedai/Qwen3.5-35B-A3B-GGUF to start chatting

How to use AesSedai/Qwen3.5-35B-A3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M

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": "AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AesSedai/Qwen3.5-35B-A3B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M

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 AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use AesSedai/Qwen3.5-35B-A3B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use AesSedai/Qwen3.5-35B-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M
```

Lemonade

How to use AesSedai/Qwen3.5-35B-A3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AesSedai/Qwen3.5-35B-A3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-35B-A3B-GGUF-Q4_K_M

List all available models

lemonade list

AesSedai commited on May 19

Commit

fc22570

0 Parent(s):

Super-squash branch 'main' using huggingface_hub

Browse files

Files changed (23) hide show

.gitattributes +50 -0
IQ3_S/Qwen3.5-35B-A3B-IQ3_S-00001-of-00002.gguf +3 -0
IQ3_S/Qwen3.5-35B-A3B-IQ3_S-00002-of-00002.gguf +3 -0
IQ4_XS/Qwen3.5-35B-A3B-IQ4_XS-00001-of-00002.gguf +3 -0
IQ4_XS/Qwen3.5-35B-A3B-IQ4_XS-00002-of-00002.gguf +3 -0
Q4_K_M/Qwen3.5-35B-A3B-Q4_K_M-00001-of-00002.gguf +3 -0
Q4_K_M/Qwen3.5-35B-A3B-Q4_K_M-00002-of-00002.gguf +3 -0
Q5_K_M/Qwen3.5-35B-A3B-Q5_K_M-00001-of-00002.gguf +3 -0
Q5_K_M/Qwen3.5-35B-A3B-Q5_K_M-00002-of-00002.gguf +3 -0
README.md +23 -0
imatrix.gguf +3 -0
kld_data/01_kld_vs_filesize.png +3 -0
kld_data/02_ppl_vs_filesize.png +3 -0
kld_data/aes_sedai/Qwen3.5-35B-A3B-IQ3_S.md +0 -0
kld_data/aes_sedai/Qwen3.5-35B-A3B-IQ4_XS.md +0 -0
kld_data/aes_sedai/Qwen3.5-35B-A3B-Q4_K_M.md +0 -0
kld_data/aes_sedai/Qwen3.5-35B-A3B-Q5_K_M.md +0 -0
kld_data/aes_sedai/Qwen3.5-35B-A3B-Q8_0.md +0 -0
kld_data/llm_quantization_data.csv +6 -0
mmproj-Qwen3.5-35B-A3B-BF16.gguf +3 -0
mmproj-Qwen3.5-35B-A3B-F16.gguf +3 -0
mmproj-Qwen3.5-35B-A3B-F32.gguf +3 -0
mmproj-Qwen3.5-35B-A3B-Q8_0.gguf +3 -0

.gitattributes ADDED Viewed

	@@ -0,0 +1,50 @@

+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+IQ3_S/Qwen3.5-35B-A3B-IQ3_S-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+IQ3_S/Qwen3.5-35B-A3B-IQ3_S-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/Qwen3.5-35B-A3B-IQ4_XS-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/Qwen3.5-35B-A3B-IQ4_XS-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_K_M/Qwen3.5-35B-A3B-Q4_K_M-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Q4_K_M/Qwen3.5-35B-A3B-Q4_K_M-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Q5_K_M/Qwen3.5-35B-A3B-Q5_K_M-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Q5_K_M/Qwen3.5-35B-A3B-Q5_K_M-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-Qwen3.5-35B-A3B-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-Qwen3.5-35B-A3B-F16.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-Qwen3.5-35B-A3B-F32.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-Qwen3.5-35B-A3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+kld_data/01_kld_vs_filesize.png filter=lfs diff=lfs merge=lfs -text
+kld_data/02_ppl_vs_filesize.png filter=lfs diff=lfs merge=lfs -text
+imatrix.gguf filter=lfs diff=lfs merge=lfs -text

IQ3_S/Qwen3.5-35B-A3B-IQ3_S-00001-of-00002.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a3da837edb7b0f719d4d799d3fcbead74bd1fb1c6ccdaf09ff7d17287a953c
+size 10943424

IQ3_S/Qwen3.5-35B-A3B-IQ3_S-00002-of-00002.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:26f03573e31ff77928bdaa11c1f7cb01aa775e4c7ee03eda89df884309de5764
+size 14475693312

IQ4_XS/Qwen3.5-35B-A3B-IQ4_XS-00001-of-00002.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:43e829ae7e4f0e11d9427a79fa674f8bb734d1f1d971e20cae023e1fb2afcd75
+size 10943424

IQ4_XS/Qwen3.5-35B-A3B-IQ4_XS-00002-of-00002.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6031edd159f46e09dd1e18bbc27043ad01259cbe0e388c5fc052193eff47742b
+size 18502127872

Q4_K_M/Qwen3.5-35B-A3B-Q4_K_M-00001-of-00002.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:03236ff4f075fced2e6697fd7cccdde7fb74a9cd04a60e7bb3708305a3f33dea
+size 10943424

Q4_K_M/Qwen3.5-35B-A3B-Q4_K_M-00002-of-00002.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e80c0a664f7ff71090d74b977f3ace777626aeb8168a3462e548891c5e628aa1
+size 23031976192

Q5_K_M/Qwen3.5-35B-A3B-Q5_K_M-00001-of-00002.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:660126363feb7a2cce52bd00161d50dc5d04d52ade8785979dc9caa9329e694f
+size 10943424

Q5_K_M/Qwen3.5-35B-A3B-Q5_K_M-00002-of-00002.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce2653157b48023db45a5d0d3c3ee5ab8e01273e506fdead6cc05b26dce7c24
+size 27142394112

README.md ADDED Viewed

	@@ -0,0 +1,23 @@

+---
+base_model:
+- Qwen/Qwen3.5-35B-A3B
+---
+## Updates
+### 3/10/2026
+I've uploaded new quants using the new fused Up + Gate conversion, this offers up to a +10% boost in prompt processing speed from my testing.
+## Description
+This repo contains specialized MoE-quants for Qwen3.5-35B-A3B. The idea being that given the huge size of the FFN tensors compared to the rest of the tensors in the model, it should be possible to achieve a better quality while keeping the overall size of the entire model smaller compared to a similar naive quantization. To that end, the quantization type default is kept in high quality and the FFN UP + FFN GATE tensors are quanted down along with the FFN DOWN tensors.
+| Quant  | Size                 | Mixture                       | PPL                 | 1-(Mean PPL(Q)/PPL(base)) | KLD                 |
+| :----- | :------------------- | :---------------------------- | :------------------ | :------------------------ | :------------------ |
+| Q8_0   | 35.19 GiB (8.51 BPW) | Q8_0                          | 6.535248 ± 0.041570 | +0.0252%                  | 0.004522 ± 0.000057 |
+| Q5_K_M | 25.28 GiB (6.12 BPW) | Q8_0 / Q5_K / Q5_K / Q6_K     | 6.534171 ± 0.041557 | +0.0087%                  | 0.006066 ± 0.000056 |
+| Q4_K_M | 21.45 GiB (5.19 BPW) | Q8_0 / Q4_K / Q4_K / Q5_K     | 6.560168 ± 0.041799 | +0.4066%                  | 0.009884 ± 0.000075 |
+| IQ4_XS | 17.23 GiB (4.17 BPW) | Q8_0 / IQ3_S / IQ3_S / IQ4_XS | 6.635447 ± 0.042320 | +1.5588%                  | 0.023868 ± 0.000204 |
+| IQ3_S  | 13.48 GiB (3.26 BPW) | Q6_K / IQ2_S / IQ2_S / IQ3_S  | 6.920209 ± 0.044626 | +5.9172%                  | 0.061977 ± 0.000394 |
+![kld_graph](kld_data/01_kld_vs_filesize.png "Chart showing Pareto KLD analysis of quants")
+![ppl_graph](kld_data/02_ppl_vs_filesize.png "Chart showing Pareto PPL analysis of quants")

imatrix.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0587dbe56de3267c2db792b115fef192baaed8565fafdfa532277a63a22f6506
+size 108291328

kld_data/01_kld_vs_filesize.png ADDED Viewed

Git LFS Details

SHA256: 58ea9444a72ebedb8b8c61355b66fb06ac851544e6b9c3238e9e4d4f9f02d602
Pointer size: 131 Bytes
Size of remote file: 160 kB

kld_data/02_ppl_vs_filesize.png ADDED Viewed