Instructions to use CMSManhattan/JiRackTernaryGemma4_26b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use CMSManhattan/JiRackTernaryGemma4_26b with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M

Use Docker

docker model run hf.co/CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M

LM Studio
Jan

vLLM

How to use CMSManhattan/JiRackTernaryGemma4_26b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CMSManhattan/JiRackTernaryGemma4_26b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CMSManhattan/JiRackTernaryGemma4_26b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M

Ollama
How to use CMSManhattan/JiRackTernaryGemma4_26b with Ollama:
```
ollama run hf.co/CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M
```
Unsloth Desktop

How to use CMSManhattan/JiRackTernaryGemma4_26b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use CMSManhattan/JiRackTernaryGemma4_26b with Docker Model Runner:
```
docker model run hf.co/CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M
```

Lemonade

How to use CMSManhattan/JiRackTernaryGemma4_26b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M

Run and chat with the model

lemonade run user.JiRackTernaryGemma4_26b-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use CMSManhattan/JiRackTernaryGemma4_26b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M

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 CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use CMSManhattan/JiRackTernaryGemma4_26b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M

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 "CMSManhattan/JiRackTernaryGemma4_26b:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

Gemma 4 26B-A4B migrated to Ternary Architedure

Gemma 4 26B-A4B (MoE) migrated to the JiRack ternary architecture.

Text-only: official vision tower dropped (~550M params), decoder kept
~26B total / ~4B active per token (128 experts, top-8)
Ternary (BitNet b1.58) QAT path for CPU / GGUF / Ollama
Vision removed for RAM/VRAM optimization . So it safes much memory for large context
Robotics, routing, coding and tool-call tags via CMSManhattan/GemmaRoboticsTokenizer

JiRack service options

Current quantizations were done from the FP16 model.
If you need custom compression or fine-tuning, please write to me and I'll perform QAT from your dataset, tailored specifically to your task.
Plus double QAT via ONNX QAT.
Adapt train process to avoid catastrophic forgetting with NDA
Adapt train process to avoid fast plateau in training with NDA
Adapts to agentic or instruct models for tool calling, using the JiRack tokenizer to enable high-quality tool calling on small models — built as a domain-specific tool expert.
Deployment and scale

Partnership

NVIDIA Inception
FISERV

Architecture

From google/gemma-4-26B-A4B-it text config:


Vocab	262,144 (tied embeddings)
Hidden	2,816
Layers	30 (5 sliding : 1 full)
Heads	16
Sliding attn	head_dim 256, KV heads 8, RoPE θ 10k, window 1024
Full attn	head_dim 512, KV heads 2, proportional RoPE θ 1e6, partial rotary 0.25, `k_eq_v` (no `v_proj`)
Dense MLP	2,112 (every token, GeGLU / `gelu_pytorch_tanh`)
Experts	128 × 704, top-8
RMSNorm	plain `x * w / rms(x)`, ε = 1e-6
Softcap	30.0
Context (ckpt)	262,144 (this export uses RoPE table 4,096 unless rebuilt)

What is ternarized: q/k/v/o, dense MLP, all 128 experts.
What stays full precision: embeddings / tied lm_head, router, norms, layer_scalar.

Class: JiRackTernaryGemma4_26b (JiRackTernaryGemma4_26b.py).

Files

config.json — Hub card + auto_map to the JiRack class
model.safetensors.index.json + model-00001-of-00013.safetensors … 00013 (~49 GB bf16)
GGUF: JiRackTernaryGemma4-26b-f16.gguf, Q8_0, Q6_K, Q5_K_M, Q4_K_M, Q3_K_M
Tokenizer: CMSManhattan/GemmaRoboticsTokenizer

Tokenizer

Use CMSManhattan/GemmaRoboticsTokenizer with this checkpoint.

Gemma 4 chat template (<|turn>user / <|turn>model / <turn|>)
Extra tags: robotics, routing (__ROBOTICS__, __CODING__, …), FIM, media, mood
Vocab: 262,251 (pad=0, eos=1)

from transformers import AutoTokenizer

tok = AutoTokenizer.from_pretrained("CMSManhattan/GemmaRoboticsTokenizer")
prompt = tok.apply_chat_template(
    [{"role": "user", "content": "Hello"}],
    add_generation_prompt=True,
    enable_thinking=False,
    tokenize=False,
)

Official google/gemma-4-26B-A4B-it tokenizer also works for plain chat (vocab 262,144).
Robotics / routing tags need the extended tokenizer.

The extra 107 tokens sit past this checkpoint’s token_emb (262,144).
They are safe in the template and in datasets; do not emit those ids until you resize_token_embeddings(len(tokenizer)) and train the new rows.

Training Notice

During Quantization-Aware Training, the routing mechanism should remain frozen. Router training should only commence once the lambda parameter reaches 1.0 and the base model's quality has been verified. (Note: "lamba" was corrected to "lambda" in these revisions, assuming it refers to the standard scaling parameter often used in QAT and straight-through estimators).

Run Notice

Please note that the model has not been tested on large contexts yet. Let me know if you notice any difference in quality compared to the original.

Chat template

Stop tokens: <turn|> (106) and <eos> (1).
Sampling (Gemma 4 rec.): temperature=1.0, top_p=0.95, top_k=64.

Quick start (PyTorch)

from transformers import AutoTokenizer
from JiRackTernaryGemma4_26b import JiRackTernaryGemma4_26b, JiRackConfig

tok = AutoTokenizer.from_pretrained("CMSManhattan/GemmaRoboticsTokenizer")
# load shards via model.safetensors.index.json into JiRackTernaryGemma4_26b
# model.set_lambda(0.0)

Or the included chat script:

export JIRACK_TOKENIZER=CMSManhattan/GemmaRoboticsTokenizer
python chat_jirack_gemma4_26b.py

GGUF / llama.cpp / Ollama

Current quants were made from the F16 export.

File	Quant	Approx. size
`JiRackTernaryGemma4-26b-f16.gguf`	F16	~50 GB
`JiRackTernaryGemma4-26b-Q8_0.gguf`	Q8_0	~28 GB
`JiRackTernaryGemma4-26b-Q6_K.gguf`	Q6_K	~22 GB
`JiRackTernaryGemma4-26b-Q5_K_M.gguf`	Q5_K_M	~19 GB
`JiRackTernaryGemma4-26b-Q4_K_M.gguf`	Q4_K_M	~16 GB
`JiRackTernaryGemma4-26b-Q3_K_M.gguf`	Q3_K_M	~13 GB

Recommended everyday: Q4_K_M.
CPU boxes without AVX2: export MKL_ENABLE_INSTRUCTIONS=AVX.

Ollama tag (when published): cmsmanhattan/JiRackTernaryGemma4-26b-q4

https://ollama.com/cmsmanhattan/JiRackTernaryGemma4-26b-q4

ollama run cmsmanhattan/JiRackTernaryGemma4-26b-q3 "Hello"
ollama run cmsmanhattan/JiRackTernaryGemma4-26b-q4 "Hello"
ollama run cmsmanhattan/JiRackTernaryGemma4-26b-q5 "Hello"
ollama run cmsmanhattan/JiRackTernaryGemma4-26b-q6 "Hello"
ollama run cmsmanhattan/JiRackTernaryGemma4-26b-q8 "Hello"

Hardware

Use	RAM	Quant
Recommended	24–32 GB	Q4_K_M
High quality	48 GB+	Q6 / Q8 / F16
Low memory	16–24 GB	Q3_K_M

bf16 safetensors need ~50 GB RAM/VRAM resident even though only ~4B params fire per token.

Lineage

Text decoder follows google/gemma-4-26B-A4B-it.
Tokenizer: CMSManhattan/GemmaRoboticsTokenizer.
This card is the JiRack ternary port, not a Google release. Do not treat upstream Gemma 4 leaderboard numbers as this checkpoint’s scores.

JiRack Codding Agent IDE

It is Agent Coding IDE for JiRack Models to run via Ollama on home PC
It good choose for Agent Coding IDE such as Cursor , Windsurf IDE or Devin IDE etc but more safe that ask you to apply changes and review.
Web site https://www.jirack.com
Plugin https://marketplace.eclipse.org/content/jirack-coding-agent
Final release version https://huggingface.co/CMSManhattan/JiRackDeltaNet_27b/resolve/main/jirack_ide_final.zip

Contact

Email: grabko@cmsmanhattan.com
Phone: +1 (516) 777-0945
New York, USA

License

MIT for the Gemma 4 base lineage.
JiRack UI / Docker / paid Ollama builds are separate commercial products.

Downloads last month: 580

Safetensors

Model size

26B params

Tensor type

BF16

Model tree for CMSManhattan/JiRackTernaryGemma4_26b

Base model

google/gemma-4-26B-A4B

Finetuned

google/gemma-4-26B-A4B-it

Quantized

(368)

this model