Instructions to use xunlinkx/Spark-X2.5-4B-oQ6e-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xunlinkx/Spark-X2.5-4B-oQ6e-fp16 with MLX:

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

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("xunlinkx/Spark-X2.5-4B-oQ6e-fp16")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use xunlinkx/Spark-X2.5-4B-oQ6e-fp16 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "xunlinkx/Spark-X2.5-4B-oQ6e-fp16"

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": "xunlinkx/Spark-X2.5-4B-oQ6e-fp16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use xunlinkx/Spark-X2.5-4B-oQ6e-fp16 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "xunlinkx/Spark-X2.5-4B-oQ6e-fp16"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "xunlinkx/Spark-X2.5-4B-oQ6e-fp16"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "xunlinkx/Spark-X2.5-4B-oQ6e-fp16",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use xunlinkx/Spark-X2.5-4B-oQ6e-fp16 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 "xunlinkx/Spark-X2.5-4B-oQ6e-fp16"

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 xunlinkx/Spark-X2.5-4B-oQ6e-fp16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use xunlinkx/Spark-X2.5-4B-oQ6e-fp16 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "xunlinkx/Spark-X2.5-4B-oQ6e-fp16"

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 "xunlinkx/Spark-X2.5-4B-oQ6e-fp16" \
  --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"

Spark-X2.5-4B — MLX oQ6e (fp16 source)

Model Details

Model Description

oQ6e-quantized MLX build (created by xunlinkx with the omlx pipeline) of XHToken/Spark-X2.5-4B for first-class, all-local serving on Apple Silicon via omlx (the MLX OpenAI-compatible server) and mlx-lm.

Attribution chain: XHToken/Spark-X2.5-4B (official base, Apache-2.0) → xunlinkx's oQ6e quantization (this repo).

This is not a new model — it is a quantization of the existing checkpoint, produced with omlx's quantize_oq_streaming(..., oq_level=6, enhanced=True) pipeline (128×512-block imatrix calibration). The -fp16 suffix records that the quantizer consumed full-precision float16 source weights (best-fidelity input), as opposed to bf16 or already-quantized sources. The mixed-bit per-layer layout is embedded in config.json (quantization / quantization_config) so it is restored automatically on load.

Developed by: xunlinkx (oQ6e quantization + MLX build, using omlx)
Base model by: XHToken (Spark-X2.5-4B)
Shared by: xunlinkx
Model type: spark2_5 text-generation decoder (MLX quantized, model_type: spark2_5)
Language(s) (NLP): multilingual (base model; Spark-X2.5 pretraining, including English/Chinese coverage)
License: Apache 2.0 (inherits the base checkpoint license)

Compatibility — Spark support required (patch it yourself until mainline)

model_type: spark2_5 loads only where native support exists. Native support is still converging (as of 2026-09-15): mlx-lm has not merged #1891, and omlx main carries a vendored patch (#3606) that no tagged release includes yet. Until then:

mlx-lm users: checkout ml-explore/mlx-lm#1891 (gh pr checkout 1891 inside a mlx-lm clone, or pip install "mlx-lm @ git+https://github.com/xunlinkx/mlx-lm@spark2_5-native"; ab1806e-era alternative for omlx-scheduler compatibility: .../xunlinkx/mlx-lm@spark2_5-backport).
omlx users: spark support is on main since jundot/omlx#3606 (2026-09-14, vendored patch, self-disabling once the native module is present) — but no tagged release includes it yet (latest stable v0.6.4 and the 0.7.0.dev pre-releases all predate it). Run omlx from source main, or apply jundot/omlx#3671 for the oQ rules + mlx-lm pin (gh pr checkout 3671).

Loading this checkpoint with an mlx-lm that predates spark2_5 support fails with an unsupported-model-type error. No other requirements: standard MLX safetensors + config.json, no custom code needed once support is present.

Quantization detail (exact, from `config.json`)

7.013 weight-bits per parameter average (group_size 64, affine). Embeddings and norms stay fp16; per-group scales add ~0.25 bpw on disk.
Layout: 6-bit base; sigmoid head gates (self_attn.g_proj) at 8-bit on 22 of 36 layers (6-bit elsewhere); attention/MLP projections lifted to 8-bit on a handful of sensitive layers each.
Sibling levels in this family: oQ4e (5.178 bpw), oQ5e (6.098 bpw), oQ8e (8.653 bpw) — see xunlinkx/Spark-X2.5-4B-oQ{e}-fp16.

Sampling (official, per the XHToken model card)

temperature 1.0, top_p 0.95, top_k −1 (disabled); thinking mode default. (Early third-party guides suggesting 0.6–0.7 do not match the official card.)

Usage

mlx_lm.generate --model xunlinkx/Spark-X2.5-4B-oQ6e-fp16 \
  -p "The secret to baking a good cake is" -m 1024 \
  --temp 1.0 --top-p 0.95

omlx serve --host 127.0.0.1 --port 8005
# model id: Spark-X2.5-4B-oQ6e-fp16 (OpenAI-compatible /v1/chat/completions)

License

Apache-2.0, inherited from XHToken/Spark-X2.5-4B.

Downloads last month: 124

Safetensors

Model size

4B params

Tensor type

U32

F16

MLX

Hardware compatibility

6-bit

Model tree for xunlinkx/Spark-X2.5-4B-oQ6e-fp16

Base model

XHToken/Spark-X2.5-4B-Base

Finetuned

XHToken/Spark-X2.5-4B

Quantized

(55)

this model

Spark-X2.5-4B — MLX oQ6e (fp16 source)

Model Details

Model Description

Compatibility — Spark support required (patch it yourself until mainline)

Quantization detail (exact, from config.json)

Sampling (official, per the XHToken model card)

Usage

License

Model tree for xunlinkx/Spark-X2.5-4B-oQ6e-fp16

Quantization detail (exact, from `config.json`)