deadbydawn101/gemma-4-E4B-mlx-4bit

pip install mlx-lm mlx-vlm

from mlx_lm import load, generate

model, tokenizer = load("deadbydawn101/gemma-4-E4B-mlx-4bit")
messages = [{"role": "user", "content": "Explain quantum entanglement simply."}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
response = generate(model, tokenizer, prompt=prompt, max_tokens=512, verbose=True)

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

model, processor = load("deadbydawn101/gemma-4-E4B-mlx-4bit")
messages = [{"role": "user", "content": [
    {"type": "image", "image": "https://example.com/photo.jpg"},
    {"type": "text",  "text": "Describe this image in detail."}
]}]
prompt = apply_chat_template(processor, model.config, messages, add_generation_prompt=True)
response = generate(model, processor, prompt=prompt, max_tokens=512)

mlx_lm.generate \
  --model deadbydawn101/gemma-4-E4B-mlx-4bit \
  --prompt "Write a Python function to find all primes below N." \
  --max-tokens 512

mlx_lm.server --model deadbydawn101/gemma-4-E4B-mlx-4bit --port 8080

ollama run hf.co/deadbydawn101/gemma-4-E4B-mlx-4bit

Dataset:  2,054 train · 109 val · SFT completions-only
Hardware: Apple M4 Max 128GB · Peak mem: 7.876 GB
Runtime:  ~6 min for 1,000 iterations @ ~190 tok/sec

Iter 10   →  2.277   ← cold start
Iter 20   →  0.097   ← style locked in fast
Iter 50   →  0.00063
Iter 100  →  0.0000398
Iter 200  →  0.0000067  (checkpoint)
Iter 1000 →  ~3.5e-7   (final)

from mlx_vlm import load, generate

model, processor = load(
    "deadbydawn101/gemma-4-E4B-mlx-4bit",
    adapter_path="deadbydawn101/gemma-4-E4B-opus-reasoning-claude-code-lora",
)

# LoRA baked directly into weights
mlx_lm.generate --model deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit --prompt "..."

from turboquant_mlx.mlx_kvcache import TurboQuantKVCache
import mlx_lm.models.cache as cache_module

# Drop-in patch — one line before loading
cache_module.make_prompt_cache = lambda model, **kw: [
    TurboQuantKVCache() for _ in range(len(model.layers))
]

from mlx_vlm import load, generate
model, processor = load("deadbydawn101/gemma-4-E4B-mlx-4bit")
# Context is now compressed automatically — run it as normal

# Install
npm install -g @google/gemini-cli

# Run against local MLX server (self-hosted with this model)
mlx_lm.server --model deadbydawn101/gemma-4-E4B-mlx-4bit --port 8080 &
gemini --baseUrl http://localhost:8080 "Analyze this codebase and suggest improvements"

# Install
npm install -g @google/gemini-cli

# Run as a coding agent against this model (via local mlx_lm server)
mlx_lm.server --model deadbydawn101/gemma-4-E4B-mlx-4bit --port 8080 &
gemini --baseUrl http://localhost:8080

# Or use directly against Gemini API (free tier: 60 req/min)
gemini

# Real example: code review with tool calling enabled
gemini --baseUrl http://localhost:8080 \
  "Review all Python files in ./src, find potential bugs, and suggest fixes"

# Gemini CLI will: read files → call tools → model reasons → produce structured output

from mlx_lm import load, generate
import json

model, tokenizer = load("deadbydawn101/gemma-4-E4B-mlx-4bit")

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string", "description": "City and country"},
                    "units": {"type": "string", "enum": ["celsius", "fahrenheit"]}
                },
                "required": ["location"]
            }
        }
    }
]

messages = [{"role": "user", "content": "What's the weather in San Jose, CA?"}]
prompt = tokenizer.apply_chat_template(
    messages,
    tools=tools,
    add_generation_prompt=True,
    tokenize=False
)
response = generate(model, tokenizer, prompt=prompt, max_tokens=256)
# Model responds with a structured tool_call in <|tool_call>...<tool_call|> format

# After tool execution, feed the result back
messages += [
    {"role": "assistant", "tool_calls": [{"function": {"name": "get_weather", "arguments": {"location": "San Jose, CA"}}}]},
    {"role": "tool", "tool_responses": [{"name": "get_weather", "response": {"temp": 72, "condition": "sunny"}}]}
]
prompt = tokenizer.apply_chat_template(messages, tools=tools, add_generation_prompt=True, tokenize=False)
final = generate(model, tokenizer, prompt=prompt, max_tokens=256)

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

model, processor = load("deadbydawn101/gemma-4-E4B-mlx-4bit")
prompt = apply_chat_template(
    processor, model.config, messages,
    tools=tools, add_generation_prompt=True
)

ollama run hf.co/deadbydawn101/gemma-4-E4B-mlx-4bit

FROM hf.co/deadbydawn101/gemma-4-E4B-mlx-4bit

SYSTEM "You are a helpful assistant with tool-use capabilities. Think through problems step by step."

PARAMETER temperature 0.7
PARAMETER num_ctx 8192

ollama create ravenx-gemma4 -f Modelfile
ollama run ravenx-gemma4

# Ollama exposes an OpenAI-compatible API automatically
curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hf.co/deadbydawn101/gemma-4-E4B-mlx-4bit",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

# mlx_lm server is faster than Ollama for Apple Silicon — uses Metal GPU directly
mlx_lm.server --model deadbydawn101/gemma-4-E4B-mlx-4bit --port 8080

# Then use any OpenAI client
curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "deadbydawn101/gemma-4-E4B-mlx-4bit", "messages": [{"role": "user", "content": "Hello!"}]}'

from mlx_lm import load
from triattention.mlx import apply_triattention_mlx

model, tokenizer = load("deadbydawn101/gemma-4-E4B-mlx-4bit")
apply_triattention_mlx(model, kv_budget=2048)

git clone https://github.com/DeadByDawn101/ravenx-inference-harness
cd ravenx-inference-harness

# Inference
python run.py --model deadbydawn101/gemma-4-E4B-mlx-4bit --prompt "Your prompt"

# TriAttention compressed
python run.py --model deadbydawn101/gemma-4-E4B-mlx-4bit --triattention --kv-budget 2048

# Local OpenAI-compatible server (works with OpenClaw)
python serve.py --model deadbydawn101/gemma-4-E4B-mlx-4bit --triattention