Instructions to use tchbcb/sami-27b-mixbit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tchbcb/sami-27b-mixbit 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 tchbcb/sami-27b-mixbit:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf tchbcb/sami-27b-mixbit:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tchbcb/sami-27b-mixbit:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf tchbcb/sami-27b-mixbit:IQ4_XS

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 tchbcb/sami-27b-mixbit:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf tchbcb/sami-27b-mixbit:IQ4_XS

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 tchbcb/sami-27b-mixbit:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tchbcb/sami-27b-mixbit:IQ4_XS

Use Docker

docker model run hf.co/tchbcb/sami-27b-mixbit:IQ4_XS

LM Studio
Jan
Ollama
How to use tchbcb/sami-27b-mixbit with Ollama:
```
ollama run hf.co/tchbcb/sami-27b-mixbit:IQ4_XS
```
Unsloth Desktop

How to use tchbcb/sami-27b-mixbit with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tchbcb/sami-27b-mixbit:IQ4_XS

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": "tchbcb/sami-27b-mixbit:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use tchbcb/sami-27b-mixbit with Docker Model Runner:
```
docker model run hf.co/tchbcb/sami-27b-mixbit:IQ4_XS
```

Lemonade

How to use tchbcb/sami-27b-mixbit with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tchbcb/sami-27b-mixbit:IQ4_XS

Run and chat with the model

lemonade run user.sami-27b-mixbit-IQ4_XS

List all available models

lemonade list

Hermes Agent

How to use tchbcb/sami-27b-mixbit with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tchbcb/sami-27b-mixbit:IQ4_XS

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 tchbcb/sami-27b-mixbit:IQ4_XS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tchbcb/sami-27b-mixbit with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tchbcb/sami-27b-mixbit:IQ4_XS

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 "tchbcb/sami-27b-mixbit:IQ4_XS" \
  --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"

samai-27b-mixbit (Q5_K_M mixed-precision GGUF)

samai-27b（Qwen/Qwen3.8-27B 手术版：PonderNet 停机位点 L35/39/43/47/51/55/59/63 + dMoE 8 专家 + MTP）经 QLoRA SFT 后，按 mixbit 静态化管线产出的 llama.cpp 混合精度权重。

静态化（相对 samai-27b 的结构变化）

组件	处理
PonderNet (L35..63 停机循环)	展开：`ponder_forced_steps=1` 单遍语义，halter/router 丢弃
dMoE 8 专家 (仅 L35..63)	按校准激活频率 f_i 加权合并为稠密 FFN（8×2176 → 17408，与稠密层同形）
MTP 模块	丢弃（推理旁路；训练时 mtp_loss_weight=0）
视觉塔 (460M)	丢弃（纯文本）
LoRA SFT (r16 α32, 124.66M)	已合并进基座权重

等价稠密模型 ≙ Qwen3_5ForCausalLM（48 linear_attention + 16 full_attention，hidden 5120），可直接用上游 llama.cpp 载入。

量化配方（与 samai-4b-mixbit 同款）

主体：Q5_K_M
Token embedding / output：Q6_K（--token-embedding-type Q6_K）

文件

文件	说明
`samai-27b-mixbit-Q5_K_M.gguf`	主权重（含 Q6_K embedding）
`sft-adapter/`（见 samai-27b 仓）	SFT 训练侧信息

用法

llama-server -m samai-27b-mixbit-Q5_K_M.gguf --host 0.0.0.0 --port 8100 -ngl 999 -c 131072 -fa

OpenAI 兼容端点 /v1/chat/completions。

来源

基座：tchbcb/samai-27b（含 SFT adapter / 训练日志 / 数据）
配方参考：tchbcb/samai-4b-mixbit

Downloads last month: 208

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for tchbcb/sami-27b-mixbit

Base model

tchbcb/samai-27b

Quantized

(1)

this model