Instructions to use SirSahOl/JevK5-chat-mlx-16bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SirSahOl/JevK5-chat-mlx-16bit 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("SirSahOl/JevK5-chat-mlx-16bit")

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)

Transformers

How to use SirSahOl/JevK5-chat-mlx-16bit with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SirSahOl/JevK5-chat-mlx-16bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SirSahOl/JevK5-chat-mlx-16bit")
model = AutoModelForCausalLM.from_pretrained("SirSahOl/JevK5-chat-mlx-16bit", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use SirSahOl/JevK5-chat-mlx-16bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SirSahOl/JevK5-chat-mlx-16bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SirSahOl/JevK5-chat-mlx-16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SirSahOl/JevK5-chat-mlx-16bit

SGLang

How to use SirSahOl/JevK5-chat-mlx-16bit with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SirSahOl/JevK5-chat-mlx-16bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SirSahOl/JevK5-chat-mlx-16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SirSahOl/JevK5-chat-mlx-16bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SirSahOl/JevK5-chat-mlx-16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

How to use SirSahOl/JevK5-chat-mlx-16bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "SirSahOl/JevK5-chat-mlx-16bit"

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": "SirSahOl/JevK5-chat-mlx-16bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use SirSahOl/JevK5-chat-mlx-16bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "SirSahOl/JevK5-chat-mlx-16bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "SirSahOl/JevK5-chat-mlx-16bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "SirSahOl/JevK5-chat-mlx-16bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use SirSahOl/JevK5-chat-mlx-16bit with Docker Model Runner:
```
docker model run hf.co/SirSahOl/JevK5-chat-mlx-16bit
```

Hermes Agent

How to use SirSahOl/JevK5-chat-mlx-16bit 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 "SirSahOl/JevK5-chat-mlx-16bit"

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 SirSahOl/JevK5-chat-mlx-16bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SirSahOl/JevK5-chat-mlx-16bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "SirSahOl/JevK5-chat-mlx-16bit"

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 "SirSahOl/JevK5-chat-mlx-16bit" \
  --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"

JevK5-mlx-16bit

16-bit MLX conversion of alibiserikbay/JevK5 optimized for Apple Silicon native GPU inference.

Converted by: SirSahOl
Source Model: alibiserikbay/JevK5
Framework: MLX by Apple
Quantization: 16-bit (Average 16.00 (unquantized bfloat16) bits per weight)
Format: safetensors
License: apache-2.0

Model Details

Architecture: Qwen3_5ForCausalLM
Parameters: ~3.7B
Context Length: 262,144 tokens
Format: MLX (Apple Silicon native GPU format)
Quantization: 16-bit (Average 16.00 (unquantized bfloat16) bits per weight)
Active VRAM Footprint: ~8.6 GB (Minimum recommended: 16 GB Unified Memory)

Quick Start

Installation

pip install mlx-lm

Usage

CLI

# Chat interactively
mlx_lm.chat --model SirSahOl/JevK5-chat-mlx-16bit

# Generate text
mlx_lm.generate --model SirSahOl/JevK5-chat-mlx-16bit --prompt "Write a short poem about artificial intelligence."

Python API (with Chat Template)

from mlx_lm import load, generate

model, tokenizer = load("SirSahOl/JevK5-chat-mlx-16bit")

messages = [
    {"role": "user", "content": "Explain quantum superposition in simple terms."}
]
prompt = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)

response = generate(model, tokenizer, prompt=prompt, verbose=True)
print(response)

Performance Benchmarks

Measured Benchmarks (Apple M1)

Metric	4-bit	8-bit
Tokens/sec	17.97	10.35
TTFT	55.74 ms	96.71 ms
Peak Memory	420.9 MB	59.7 MB

Benchmarked on Apple M1 with 8GB unified memory. Average over 5 runs with 256 max tokens.

Multi-Quantization Comparison

Evaluate your hardware budget and choose the optimal precision:

Variant	Disk Size	VRAM Footprint	Target Apple Silicon Hardware	Key Advantage
4-bit MLX	~2.4 GB	~2.4 GB	M1 / M2 / M3 / M4 (8GB+)	Maximum generation speed and lowest RAM overhead.
8-bit MLX	~4.3 GB	~4.3 GB	M1 / M2 / M3 / M4 Pro/Max (16GB+)	Balanced accuracy and generation speed; near-lossless reasoning.
16-bit MLX (This Repository)	~8.2 GB	~8.2 GB	M2 / M3 / M4 Max/Ultra (32GB+)	Full unquantized precision; reference evaluation quality.

Who Should Use This?

Your Hardware	Recommended Quantization
M1/M2/M3/M4 (8GB – 16GB)	4-bit — Best balance of speed, low memory, and multitasking capability
M1/M2/M3/M4 Pro/Max (18GB – 36GB)	8-bit — Higher quality reasoning with comfortable memory headroom
M1/M2/M3/M4 Max/Ultra (36GB – 192GB)	16-bit — Unquantized full precision, zero quality degradation

General guidance:

Use 4-bit if you want to run this model alongside IDEs, browsers, and background development tools.
Use 8-bit if you have 16GB+ unified memory and require superior reasoning and code accuracy.
Use 16-bit for research, benchmarking, evaluation, or high-end workstation deployments.

Other Quantization Variants

Variant	Link
4-bit	SirSahOl/JevK5-chat-mlx-4bit
8-bit	SirSahOl/JevK5-chat-mlx-8bit
16-bit	SirSahOl/JevK5-chat-mlx-16bit

LM Studio & Local Inference Setup Guide

To prevent runaway loops and ensure correct conversational turn-taking, configure custom stop tokens in your local inference runtime:

<|im_start|>
<|im_end|>
<|endoftext|>

Prompt Template Formatting

System Prefix: <|im_start|>system\n
System Suffix: <|im_end|>\n
User Prefix: <|im_start|>user\n
Assistant Suffix: <|im_end|>\n<|im_start|>assistant\n

Ollama Quickstart

FROM SirSahOl/JevK5-chat-mlx-16bit
PARAMETER stop "<|im_start|>"
PARAMETER stop "<|im_end|>"
PARAMETER stop "<|endoftext|>"
PARAMETER temperature 0.7

ollama create jevk5-chat-mlx-16bit -f Modelfile
ollama run jevk5-chat-mlx-16bit

Conversion Details

Property	Value
Source Model	alibiserikbay/JevK5
Quantization	16-bit
mlx-lm Version	0.31.3
Conversion Time	127.6s
Output Size	7.9 GB
Date	2026-10-01T01:20:31.239815+00:00

Reproduction

To reproduce this conversion:

pip install mlx-lm==0.31.3
python3 -m mlx_lm.convert --hf-path alibiserikbay/JevK5 --mlx-path output/JevK5-mlx-16bit

Limitations & Known Issues

4-bit group-wise quantization introduces minor precision loss compared to unquantized weights; for deep mathematical derivations or precision-critical reasoning, test the 8-bit or 16-bit variants.
High context sequences (>32K tokens) require sufficient unified memory headroom; ensure unified memory is not overcommitted.
This is a weight-only MLX conversion designed specifically for Apple Silicon GPUs (M1/M2/M3/M4 series).