Instructions to use TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp")
config = load_config("TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp"

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 TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp"

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 "TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

TokenAI-zer commited on 11 days ago

Commit

f58e5f7

verified ·

1 Parent(s): c1ea340

Update references after account rename

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -35,7 +35,7 @@ I am not affiliated with UkisAI. All upstream weights, benchmarks and license te
 ## Pick a variant
-| | [oQ4-mtp](https://huggingface.co/suzu89/Swift-Qwen3.8-27b-oQ4-mtp) | [oQ6-mtp](https://huggingface.co/suzu89/Swift-Qwen3.8-27b-oQ6-mtp) | [oQ8-mtp](https://huggingface.co/suzu89/Swift-Qwen3.8-27b-oQ8-mtp) |
 |---|---|---|---|
 | Weights on disk | 15.81 GiB (16.97 GB), 4 shards | 22.09 GiB (23.72 GB), 5 shards | 27.94 GiB (30.00 GB), 6 shards |
 | Weight precision | mixed 4/5-bit | mixed 6/8-bit | uniform 8-bit |
@@ -78,7 +78,7 @@ Precision is mixed per module and recorded verbatim in `config.json` → `quanti
 ```bash
 # 1. drop the folder into the oMLX model dir
-git clone https://huggingface.co/suzu89/Swift-Qwen3.8-27b-oQ4-mtp ~/.omlx/models/Swift-Qwen3.8-27b-oQ4-mtp
 # 2. start the multi-model server (model id = folder name)
 omlx serve --model-dir ~/.omlx/models --port 8000
@@ -105,7 +105,7 @@ In oMLX model settings, enable the speculative head and the matching reasoning p
 ```bash
 pip install -U mlx-lm mlx-vlm
-python -m mlx_lm.server --model suzu89/Swift-Qwen3.8-27b-oQ4-mtp --port 8000
 ```
 Only oMLX 0.6.4 is verified by me; if you get `mlx_lm` running this architecture, please open an issue and I will document it.
@@ -162,9 +162,9 @@ Measured throughput/acceptance-length data and issue reports (especially "quant
 ```bibtex
 @misc{swift-qwen3.8-27b-mlx-quants,
   title   = {Swift-Qwen3.8-27b-oQ4-mtp}: oMLX/MLX quantization of Swift-Qwen3.8-27B with MTP head retained,
-  author  = {suzu89},
   year    = {2026},
-  howpublished = {\url{https://huggingface.co/suzu89/Swift-Qwen3.8-27b-oQ4-mtp}},
   note    = {Unofficial quantization of ukisai/Swift-Qwen3.8-27b}
 }

 ## Pick a variant
+| | [oQ4-mtp](https://huggingface.co/TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp) | [oQ6-mtp](https://huggingface.co/TokenAI-zer/Swift-Qwen3.8-27b-oQ6-mtp) | [oQ8-mtp](https://huggingface.co/TokenAI-zer/Swift-Qwen3.8-27b-oQ8-mtp) |
 |---|---|---|---|
 | Weights on disk | 15.81 GiB (16.97 GB), 4 shards | 22.09 GiB (23.72 GB), 5 shards | 27.94 GiB (30.00 GB), 6 shards |
 | Weight precision | mixed 4/5-bit | mixed 6/8-bit | uniform 8-bit |
 ```bash
 # 1. drop the folder into the oMLX model dir
+git clone https://huggingface.co/TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp ~/.omlx/models/Swift-Qwen3.8-27b-oQ4-mtp
 # 2. start the multi-model server (model id = folder name)
 omlx serve --model-dir ~/.omlx/models --port 8000
 ```bash
 pip install -U mlx-lm mlx-vlm
+python -m mlx_lm.server --model TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp --port 8000
 ```
 Only oMLX 0.6.4 is verified by me; if you get `mlx_lm` running this architecture, please open an issue and I will document it.
 ```bibtex
 @misc{swift-qwen3.8-27b-mlx-quants,
   title   = {Swift-Qwen3.8-27b-oQ4-mtp}: oMLX/MLX quantization of Swift-Qwen3.8-27B with MTP head retained,
+  author  = {TokenAI-zer},
   year    = {2026},
+  howpublished = {\url{https://huggingface.co/TokenAI-zer/Swift-Qwen3.8-27b-oQ4-mtp}},
   note    = {Unofficial quantization of ukisai/Swift-Qwen3.8-27b}
 }