Instructions to use mlx-community/Nex-N2.5-mini-oQ4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Nex-N2.5-mini-oQ4 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("mlx-community/Nex-N2.5-mini-oQ4")

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 mlx-community/Nex-N2.5-mini-oQ4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Nex-N2.5-mini-oQ4"

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": "mlx-community/Nex-N2.5-mini-oQ4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use mlx-community/Nex-N2.5-mini-oQ4 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/Nex-N2.5-mini-oQ4"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Nex-N2.5-mini-oQ4"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/Nex-N2.5-mini-oQ4",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use mlx-community/Nex-N2.5-mini-oQ4 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 "mlx-community/Nex-N2.5-mini-oQ4"

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 mlx-community/Nex-N2.5-mini-oQ4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlx-community/Nex-N2.5-mini-oQ4 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Nex-N2.5-mini-oQ4"

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 "mlx-community/Nex-N2.5-mini-oQ4" \
  --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"

Nex-N2.5-mini oQ4 (MLX)

oQ4 (streaming) MLX conversion of nex-agi/Nex-N2.5-mini, a 35B-parameter Mixture-of-Exerts (MoE) agentic model with 3B active parameters.

Upstream model: Nex-N2.5-mini by Nex-AGI (Shanghai Innovation Institute), released under Apache 2.0.

Conversion: Quantized to MLX format using Hermes Agent with oMLX (streaming oQ4). Sensitivity-driven mixed-precision with per-layer bit allocation.

Architecture

Property	Value
Type	Qwen3.5 MoE (Hybrid Attention)
Total params	35B
Active params	3B (8 routed + 1 shared expert)
Layers	40
Experts	256
Context length	262K tokens
Hidden size	2048

Quickstart

pip install -U mlx-lm

# Generate
python3 -m mlx_lm.generate \
  --model hermitdave/Nex-N2.5-mini-oQ4 \
  --prompt "Explain why long-context evaluation is difficult." \
  --max-tokens 512 --temp 1.0 --top-p 0.95

# Chat (with reasoning)
python3 -m mlx_lm.chat --model hermitdave/Nex-N2.5-mini-oQ4

Via OpenAI-compatible server

omlx serve hermitdave/Nex-N2.5-mini-oQ4 --port 8000

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
response = client.chat.completions.create(
    model="hermitdave/Nex-N2.5-mini-oQ4",
    messages=[{"role": "user", "content": "Explain quantum entanglement."}],
    extra_body={"chat_template_kwargs": {"reasoning_effort": "high"}},
)
print("Reasoning:", getattr(response.choices[0].message, "reasoning_content", None))
print("Answer:", response.choices[0].message.content)

Reasoning Modes

Use reasoning_effort to control thinking behavior:

`reasoning_effort`	Mode	Behavior
`"none"`	Non-thinking	Respond directly without reasoning trace
`"medium"` (default)	Adaptive thinking	Model decides whether/how much to think
`"high"`	Thinking	Always enable thinking before responding

Conversion Details

Method: oQ4 (streaming) via oMLX
Bits-per-weight: ~4.6 (mixed precision, sensitivity-driven)
Router protection: MoE router gates preserved at 8-bit
lm_head: 8-bit
Output size: 19 GB (27% of bf16 source)
Validated: ✅ Smoke test passed (coherent generation, EOS functional)

Performance

Upstream Benchmarks (Nex-N2.5-mini, bf16)

Benchmark	Score
Terminal-Bench 2.1	73.4
SWE-Bench Pro	43.8
AutomationBench v1.0.6	32.3
Toolathlon Verified	54.6
BrowseComp	83.4
OSWorld-Verified	71.2
WebArena-Verified	63.4

See Nex-N2.5 announcement for full evaluation details.

Deployment

Minimum RAM: 24 GB (for 19 GB model + inference overhead)
Recommended: Apple Silicon M1 Max or better
Context: 262K tokens native, extensible to 1M

Known Limitations

MTP disabled: Source config claims MTP (mtp_num_hidden_layers: 1) but checkpoint has no mtp.* weights — speculative decoding via MTP unavailable
Hybrid attention: Fine generation speed, slower long-context prefill (recurrent state layers)

License

Apache 2.0 (same as upstream). See Nex-N2.5 license.

Downloads last month: -

Safetensors

Model size

35B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for mlx-community/Nex-N2.5-mini-oQ4

Base model

nex-agi/Nex-N2.5-mini

Quantized

(28)

this model