Instructions to use donghanasd/Agents-A1-TQ3_4S-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 donghanasd/Agents-A1-TQ3_4S-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 donghanasd/Agents-A1-TQ3_4S-GGUF
# Run inference directly in the terminal:
llama cli -hf donghanasd/Agents-A1-TQ3_4S-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf donghanasd/Agents-A1-TQ3_4S-GGUF
# Run inference directly in the terminal:
llama cli -hf donghanasd/Agents-A1-TQ3_4S-GGUF

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 donghanasd/Agents-A1-TQ3_4S-GGUF
# Run inference directly in the terminal:
./llama-cli -hf donghanasd/Agents-A1-TQ3_4S-GGUF

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 donghanasd/Agents-A1-TQ3_4S-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf donghanasd/Agents-A1-TQ3_4S-GGUF

Use Docker

docker model run hf.co/donghanasd/Agents-A1-TQ3_4S-GGUF

LM Studio
Jan
Ollama
How to use donghanasd/Agents-A1-TQ3_4S-GGUF with Ollama:
```
ollama run hf.co/donghanasd/Agents-A1-TQ3_4S-GGUF
```
Unsloth Desktop

How to use donghanasd/Agents-A1-TQ3_4S-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf donghanasd/Agents-A1-TQ3_4S-GGUF

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "donghanasd/Agents-A1-TQ3_4S-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use donghanasd/Agents-A1-TQ3_4S-GGUF with Docker Model Runner:
```
docker model run hf.co/donghanasd/Agents-A1-TQ3_4S-GGUF
```

Lemonade

How to use donghanasd/Agents-A1-TQ3_4S-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull donghanasd/Agents-A1-TQ3_4S-GGUF

Run and chat with the model

lemonade run user.Agents-A1-TQ3_4S-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use donghanasd/Agents-A1-TQ3_4S-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 donghanasd/Agents-A1-TQ3_4S-GGUF

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 donghanasd/Agents-A1-TQ3_4S-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use donghanasd/Agents-A1-TQ3_4S-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf donghanasd/Agents-A1-TQ3_4S-GGUF

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 "donghanasd/Agents-A1-TQ3_4S-GGUF" \
  --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"

Agents-A1 — TQ3_4S GGUF

A TQ3_4S (~Q3) mixed-precision quantized GGUF of InternScience/Agents-A1 (a 35B qwen35moe Mixture-of-Experts agent model), weighing in at **13 GB**. Built to run on a single 16 GB GPU (e.g. RTX 5060 Ti).

Quantized from the official F16 GGUF (InternScience/Agents-A1-F16-GGUF, 69 GB) using the same mixed K-quant + TQ3_4S tensor layout as the YTan2000/Qwen3.6-35B-A3B-MTP-TQ3_4S recipe (both are the same qwen35moe architecture).

Files

File	Size	Notes
`Agents-A1-TQ3_4S.gguf`	~13 GB	Mixed K-quant + TQ3_4S layout

Quantization recipe

Base ftype Q3_K_M with per-tensor overrides (only the SSM special tensors are TQ3_4S; everything else is a mixed K-quant layout):

token_embd                       = Q5_K
output                           = Q4_K
attn_* / *_shexp / ssm_out       = Q6_K
ffn_gate_exps / ffn_up_exps      = Q2_K
ffn_down_exps                    = Q3_K   (Q4_K on blocks 21, 28, 38)
ssm_alpha / ssm_beta             = TQ3_4S

Verified output layout (733 tensors):

Q2_K    x80    7.05 GB   (expert gate/up)
Q3_K    x37    4.27 GB   (expert down)
Q6_K   x250    1.15 GB   (attention / shared-expert / ssm_out)
Q4_K     x4    0.74 GB   (output + down_exps blk 21/28/38)
Q5_K     x1    0.35 GB   (token_embd)
TQ3_4S  x60   ~0   GB   (ssm_alpha / ssm_beta)
F32    x301    0.09 GB   (norms / biases)

Produced with llama-quantize:

llama-quantize \
  --token-embedding-type Q5_K \
  --output-tensor-type Q4_K \
  --tensor-type-file tensor_types.txt \
  Agents-A1-F16.gguf \
  Agents-A1-TQ3_4S.gguf \
  Q3_K_M

No MTP: unlike the Qwen3.6-35B reference, Agents-A1 has no native MTP (nextn) draft head, so there is no --spec-type draft-mtp speculative decoding with this model.

Tooling

Built with the turbo-tan/llama.cpp-tq3 fork, which adds the TQ3_4S quantization type.

⚠️ Version note: this file was produced with a recent fork build where the TQ3_4S ggml type id is 46. You must run it with an up-to-date build of the same fork — older builds (type id 45) will fail to load it.

Running with `llama-server`

llama-server \
  --host 0.0.0.0 --port 8080 \
  --model Agents-A1-TQ3_4S.gguf \
  --jinja \
  -ngl 99 \
  -fa on \
  -ctk q8_0 -ctv q8_0 \
  --batch-size 2048 --ubatch-size 512 \
  --ctx-size 64000 \
  --parallel 1 -np 1 \
  --reasoning on --reasoning-format auto \
  --warmup --perf \
  --threads 4 --threads-batch 8 \
  --cache-ram 16000 --ctx-checkpoints 32

Notes:

--ctx-size 64000 is roughly the empirical max on 16 GB; lower it on OOM.
-ctk q8_0 -ctv q8_0 quantizes the KV cache to fit more context.
To disable reasoning: replace --reasoning on with --reasoning off --reasoning-budget 0.

Sources / Attribution

Base weights: InternScience/Agents-A1-F16-GGUF / InternScience/Agents-A1
Recipe reference: YTan2000/Qwen3.6-35B-A3B-MTP-TQ3_4S
Tooling: turbo-tan/llama.cpp-tq3

License and usage follow the base model — see InternScience/Agents-A1.

Downloads last month: 50

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for donghanasd/Agents-A1-TQ3_4S-GGUF

Base model

InternScience/Agents-A1

Quantized

InternScience/Agents-A1-F16-GGUF

Quantized

(1)

this model

Agents-A1 — TQ3_4S GGUF

Files

Quantization recipe

Tooling

Running with llama-server

Sources / Attribution

Model tree for donghanasd/Agents-A1-TQ3_4S-GGUF

Running with `llama-server`