Instructions to use tchbcb/samai-9b 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/samai-9b 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/samai-9b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tchbcb/samai-9b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tchbcb/samai-9b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tchbcb/samai-9b: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 tchbcb/samai-9b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tchbcb/samai-9b: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 tchbcb/samai-9b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tchbcb/samai-9b:Q4_K_M

Use Docker

docker model run hf.co/tchbcb/samai-9b:Q4_K_M

LM Studio
Jan
Ollama
How to use tchbcb/samai-9b with Ollama:
```
ollama run hf.co/tchbcb/samai-9b:Q4_K_M
```
Unsloth Desktop

How to use tchbcb/samai-9b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tchbcb/samai-9b: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": "tchbcb/samai-9b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use tchbcb/samai-9b with Docker Model Runner:
```
docker model run hf.co/tchbcb/samai-9b:Q4_K_M
```

Lemonade

How to use tchbcb/samai-9b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tchbcb/samai-9b:Q4_K_M

Run and chat with the model

lemonade run user.samai-9b-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use tchbcb/samai-9b 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/samai-9b: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 tchbcb/samai-9b:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tchbcb/samai-9b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tchbcb/samai-9b: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 "tchbcb/samai-9b: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"

samai-9b / m13_r13_alloc.json

tchbcb

Upload m13_r13_alloc.json with huggingface_hub

c62a5e3 verified 24 days ago

Raw History Blame Contribute Delete

12.3 kB

{"table": {"output": "q6_k", "output_norm": "q6_k", "token_embd": "q6_k", "blk.0.attn_gate": "q6_k", "blk.0.attn_norm": "q6_k", "blk.0.attn_qkv": "q6_k", "blk.0.ffn_down": "q5_0", "blk.0.ffn_gate": "q4_0", "blk.0.ffn_up": "q4_0", "blk.0.post_attention_norm": "q6_k", "blk.0.ssm_a": "q6_k", "blk.0.ssm_alpha": "q6_k", "blk.0.ssm_beta": "q6_k", "blk.0.ssm_conv1d": "q6_k", "blk.0.ssm_dt.bias": "q6_k", "blk.0.ssm_norm": "q6_k", "blk.0.ssm_out": "q6_k", "blk.1.attn_gate": "q6_k", "blk.1.attn_norm": "q6_k", "blk.1.attn_qkv": "q6_k", "blk.1.ffn_down": "q5_0", "blk.1.ffn_gate": "q4_0", "blk.1.ffn_up": "q4_0", "blk.1.post_attention_norm": "q6_k", "blk.1.ssm_a": "q6_k", "blk.1.ssm_alpha": "q6_k", "blk.1.ssm_beta": "q6_k", "blk.1.ssm_conv1d": "q6_k", "blk.1.ssm_dt.bias": "q6_k", "blk.1.ssm_norm": "q6_k", "blk.1.ssm_out": "q6_k", "blk.2.attn_gate": "q6_k", "blk.2.attn_norm": "q6_k", "blk.2.attn_qkv": "q6_k", "blk.2.ffn_down": "q5_0", "blk.2.ffn_gate": "q4_0", "blk.2.ffn_up": "q4_0", "blk.2.post_attention_norm": "q6_k", "blk.2.ssm_a": "q6_k", "blk.2.ssm_alpha": "q6_k", "blk.2.ssm_beta": "q6_k", "blk.2.ssm_conv1d": "q6_k", "blk.2.ssm_dt.bias": "q6_k", "blk.2.ssm_norm": "q6_k", "blk.2.ssm_out": "q6_k", "blk.3.attn_k": "q6_k", "blk.3.attn_k_norm": "q6_k", "blk.3.attn_norm": "q6_k", "blk.3.attn_output": "q6_k", "blk.3.attn_q": "q6_k", "blk.3.attn_q_norm": "q6_k", "blk.3.attn_v": "q6_k", "blk.3.ffn_down": "q5_0", "blk.3.ffn_gate": "q4_0", "blk.3.ffn_up": "q4_0", "blk.3.post_attention_norm": "q6_k", "blk.4.attn_gate": "q6_k", "blk.4.attn_norm": "q6_k", "blk.4.attn_qkv": "q6_k", "blk.4.ffn_down": "q5_0", "blk.4.ffn_gate": "q4_0", "blk.4.ffn_up": "q4_0", "blk.4.post_attention_norm": "q6_k", "blk.4.ssm_a": "q6_k", "blk.4.ssm_alpha": "q6_k", "blk.4.ssm_beta": "q6_k", "blk.4.ssm_conv1d": "q6_k", "blk.4.ssm_dt.bias": "q6_k", "blk.4.ssm_norm": "q6_k", "blk.4.ssm_out": "q6_k", "blk.5.attn_gate": "q6_k", "blk.5.attn_norm": "q6_k", "blk.5.attn_qkv": "q6_k", "blk.5.ffn_down": "q5_0", "blk.5.ffn_gate": "q4_0", "blk.5.ffn_up": "q4_0", "blk.5.post_attention_norm": "q6_k", "blk.5.ssm_a": "q6_k", "blk.5.ssm_alpha": "q6_k", "blk.5.ssm_beta": "q6_k", "blk.5.ssm_conv1d": "q6_k", "blk.5.ssm_dt.bias": "q6_k", "blk.5.ssm_norm": "q6_k", "blk.5.ssm_out": "q6_k", "blk.6.attn_gate": "q6_k", "blk.6.attn_norm": "q6_k", "blk.6.attn_qkv": "q6_k", "blk.6.ffn_down": "q5_0", "blk.6.ffn_gate": "q4_0", "blk.6.ffn_up": "q4_0", "blk.6.post_attention_norm": "q6_k", "blk.6.ssm_a": "q6_k", "blk.6.ssm_alpha": "q6_k", "blk.6.ssm_beta": "q6_k", "blk.6.ssm_conv1d": "q6_k", "blk.6.ssm_dt.bias": "q6_k", "blk.6.ssm_norm": "q6_k", "blk.6.ssm_out": "q6_k", "blk.7.attn_k": "q6_k", "blk.7.attn_k_norm": "q6_k", "blk.7.attn_norm": "q6_k", "blk.7.attn_output": "q6_k", "blk.7.attn_q": "q6_k", "blk.7.attn_q_norm": "q6_k", "blk.7.attn_v": "q6_k", "blk.7.ffn_down": "q5_0", "blk.7.ffn_gate": "q4_0", "blk.7.ffn_up": "q4_0", "blk.7.post_attention_norm": "q6_k", "blk.8.attn_gate": "q6_k", "blk.8.attn_norm": "q6_k", "blk.8.attn_qkv": "q6_k", "blk.8.ffn_down": "q5_0", "blk.8.ffn_gate": "q4_0", "blk.8.ffn_up": "q4_0", "blk.8.post_attention_norm": "q6_k", "blk.8.ssm_a": "q6_k", "blk.8.ssm_alpha": "q6_k", "blk.8.ssm_beta": "q6_k", "blk.8.ssm_conv1d": "q6_k", "blk.8.ssm_dt.bias": "q6_k", "blk.8.ssm_norm": "q6_k", "blk.8.ssm_out": "q6_k", "blk.9.attn_gate": "q6_k", "blk.9.attn_norm": "q6_k", "blk.9.attn_qkv": "q6_k", "blk.9.ffn_down": "q5_0", "blk.9.ffn_gate": "q4_0", "blk.9.ffn_up": "q4_0", "blk.9.post_attention_norm": "q6_k", "blk.9.ssm_a": "q6_k", "blk.9.ssm_alpha": "q6_k", "blk.9.ssm_beta": "q6_k", "blk.9.ssm_conv1d": "q6_k", "blk.9.ssm_dt.bias": "q6_k", "blk.9.ssm_norm": "q6_k", "blk.9.ssm_out": "q6_k", "blk.10.attn_gate": "q6_k", "blk.10.attn_norm": "q6_k", "blk.10.attn_qkv": "q6_k", "blk.10.ffn_down": "q5_0", "blk.10.ffn_gate": "q4_0", "blk.10.ffn_up": "q4_0", "blk.10.post_attention_norm": "q6_k", "blk.10.ssm_a": "q6_k", "blk.10.ssm_alpha": "q6_k", "blk.10.ssm_beta": "q6_k", "blk.10.ssm_conv1d": "q6_k", "blk.10.ssm_dt.bias": "q6_k", "blk.10.ssm_norm": "q6_k", "blk.10.ssm_out": "q6_k", "blk.11.attn_k": "q6_k", "blk.11.attn_k_norm": "q6_k", "blk.11.attn_norm": "q6_k", "blk.11.attn_output": "q6_k", "blk.11.attn_q": "q6_k", "blk.11.attn_q_norm": "q6_k", "blk.11.attn_v": "q6_k", "blk.11.ffn_down": "q5_0", "blk.11.ffn_gate": "q4_0", "blk.11.ffn_up": "q4_0", "blk.11.post_attention_norm": "q6_k", "blk.12.attn_gate": "q6_k", "blk.12.attn_norm": "q6_k", "blk.12.attn_qkv": "q6_k", "blk.12.ffn_down": "q5_0", "blk.12.ffn_gate": "q4_0", "blk.12.ffn_up": "q4_0", "blk.12.post_attention_norm": "q6_k", "blk.12.ssm_a": "q6_k", "blk.12.ssm_alpha": "q6_k", "blk.12.ssm_beta": "q6_k", "blk.12.ssm_conv1d": "q6_k", "blk.12.ssm_dt.bias": "q6_k", "blk.12.ssm_norm": "q6_k", "blk.12.ssm_out": "q6_k", "blk.13.attn_gate": "q6_k", "blk.13.attn_norm": "q6_k", "blk.13.attn_qkv": "q6_k", "blk.13.ffn_down": "q5_0", "blk.13.ffn_gate": "q4_0", "blk.13.ffn_up": "q4_0", "blk.13.post_attention_norm": "q6_k", "blk.13.ssm_a": "q6_k", "blk.13.ssm_alpha": "q6_k", "blk.13.ssm_beta": "q6_k", "blk.13.ssm_conv1d": "q6_k", "blk.13.ssm_dt.bias": "q6_k", "blk.13.ssm_norm": "q6_k", "blk.13.ssm_out": "q6_k", "blk.14.attn_gate": "q6_k", "blk.14.attn_norm": "q6_k", "blk.14.attn_qkv": "q6_k", "blk.14.ffn_down": "q5_0", "blk.14.ffn_gate": "q4_0", "blk.14.ffn_up": "q4_0", "blk.14.post_attention_norm": "q6_k", "blk.14.ssm_a": "q6_k", "blk.14.ssm_alpha": "q6_k", "blk.14.ssm_beta": "q6_k", "blk.14.ssm_conv1d": "q6_k", "blk.14.ssm_dt.bias": "q6_k", "blk.14.ssm_norm": "q6_k", "blk.14.ssm_out": "q6_k", "blk.15.attn_k": "q6_k", "blk.15.attn_k_norm": "q6_k", "blk.15.attn_norm": "q6_k", "blk.15.attn_output": "q6_k", "blk.15.attn_q": "q6_k", "blk.15.attn_q_norm": "q6_k", "blk.15.attn_v": "q6_k", "blk.15.ffn_down": "q5_0", "blk.15.ffn_gate": "q4_0", "blk.15.ffn_up": "q4_0", "blk.15.post_attention_norm": "q6_k", "blk.16.attn_gate": "q6_k", "blk.16.attn_norm": "q6_k", "blk.16.attn_qkv": "q6_k", "blk.16.ffn_down": "q5_0", "blk.16.ffn_gate": "q4_0", "blk.16.ffn_up": "q4_0", "blk.16.post_attention_norm": "q6_k", "blk.16.ssm_a": "q6_k", "blk.16.ssm_alpha": "q6_k", "blk.16.ssm_beta": "q6_k", "blk.16.ssm_conv1d": "q6_k", "blk.16.ssm_dt.bias": "q6_k", "blk.16.ssm_norm": "q6_k", "blk.16.ssm_out": "q6_k", "blk.17.attn_gate": "q6_k", "blk.17.attn_norm": "q6_k", "blk.17.attn_qkv": "q6_k", "blk.17.ffn_down": "q5_0", "blk.17.ffn_gate": "q4_0", "blk.17.ffn_up": "q4_0", "blk.17.post_attention_norm": "q6_k", "blk.17.ssm_a": "q6_k", "blk.17.ssm_alpha": "q6_k", "blk.17.ssm_beta": "q6_k", "blk.17.ssm_conv1d": "q6_k", "blk.17.ssm_dt.bias": "q6_k", "blk.17.ssm_norm": "q6_k", "blk.17.ssm_out": "q6_k", "blk.18.attn_gate": "q6_k", "blk.18.attn_norm": "q6_k", "blk.18.attn_qkv": "q6_k", "blk.18.ffn_down": "q5_0", "blk.18.ffn_gate": "q4_0", "blk.18.ffn_up": "q4_0", "blk.18.post_attention_norm": "q6_k", "blk.18.ssm_a": "q6_k", "blk.18.ssm_alpha": "q6_k", "blk.18.ssm_beta": "q6_k", "blk.18.ssm_conv1d": "q6_k", "blk.18.ssm_dt.bias": "q6_k", "blk.18.ssm_norm": "q6_k", "blk.18.ssm_out": "q6_k", "blk.19.attn_k": "q6_k", "blk.19.attn_k_norm": "q6_k", "blk.19.attn_norm": "q6_k", "blk.19.attn_output": "q6_k", "blk.19.attn_q": "q6_k", "blk.19.attn_q_norm": "q6_k", "blk.19.attn_v": "q6_k", "blk.19.ffn_down": "q5_0", "blk.19.ffn_gate": "q4_0", "blk.19.ffn_up": "q4_0", "blk.19.post_attention_norm": "q6_k", "blk.20.attn_gate": "q6_k", "blk.20.attn_norm": "q6_k", "blk.20.attn_qkv": "q6_k", "blk.20.ffn_down": "q5_0", "blk.20.ffn_gate": "q4_0", "blk.20.ffn_up": "q4_0", "blk.20.post_attention_norm": "q6_k", "blk.20.ssm_a": "q6_k", "blk.20.ssm_alpha": "q6_k", "blk.20.ssm_beta": "q6_k", "blk.20.ssm_conv1d": "q6_k", "blk.20.ssm_dt.bias": "q6_k", "blk.20.ssm_norm": "q6_k", "blk.20.ssm_out": "q6_k", "blk.21.attn_gate": "q6_k", "blk.21.attn_norm": "q6_k", "blk.21.attn_qkv": "q6_k", "blk.21.ffn_down": "q5_0", "blk.21.ffn_gate": "q4_0", "blk.21.ffn_up": "q4_0", "blk.21.post_attention_norm": "q6_k", "blk.21.ssm_a": "q6_k", "blk.21.ssm_alpha": "q6_k", "blk.21.ssm_beta": "q6_k", "blk.21.ssm_conv1d": "q6_k", "blk.21.ssm_dt.bias": "q6_k", "blk.21.ssm_norm": "q6_k", "blk.21.ssm_out": "q6_k", "blk.22.attn_gate": "q6_k", "blk.22.attn_norm": "q6_k", "blk.22.attn_qkv": "q6_k", "blk.22.ffn_down": "q5_0", "blk.22.ffn_gate": "q4_0", "blk.22.ffn_up": "q4_0", "blk.22.post_attention_norm": "q6_k", "blk.22.ssm_a": "q6_k", "blk.22.ssm_alpha": "q6_k", "blk.22.ssm_beta": "q6_k", "blk.22.ssm_conv1d": "q6_k", "blk.22.ssm_dt.bias": "q6_k", "blk.22.ssm_norm": "q6_k", "blk.22.ssm_out": "q6_k", "blk.23.attn_k": "q6_k", "blk.23.attn_k_norm": "q6_k", "blk.23.attn_norm": "q6_k", "blk.23.attn_output": "q6_k", "blk.23.attn_q": "q6_k", "blk.23.attn_q_norm": "q6_k", "blk.23.attn_v": "q6_k", "blk.23.ffn_down": "q5_0", "blk.23.ffn_gate": "q4_0", "blk.23.ffn_up": "q4_0", "blk.23.post_attention_norm": "q6_k", "blk.24.attn_gate": "q6_k", "blk.24.attn_norm": "q6_k", "blk.24.attn_qkv": "q6_k", "blk.24.ffn_down": "q5_0", "blk.24.ffn_gate": "q4_0", "blk.24.ffn_up": "q4_0", "blk.24.post_attention_norm": "q6_k", "blk.24.ssm_a": "q6_k", "blk.24.ssm_alpha": "q6_k", "blk.24.ssm_beta": "q6_k", "blk.24.ssm_conv1d": "q6_k", "blk.24.ssm_dt.bias": "q6_k", "blk.24.ssm_norm": "q6_k", "blk.24.ssm_out": "q6_k", "blk.25.attn_gate": "q6_k", "blk.25.attn_norm": "q6_k", "blk.25.attn_qkv": "q6_k", "blk.25.ffn_down": "q5_0", "blk.25.ffn_gate": "q4_0", "blk.25.ffn_up": "q4_0", "blk.25.post_attention_norm": "q6_k", "blk.25.ssm_a": "q6_k", "blk.25.ssm_alpha": "q6_k", "blk.25.ssm_beta": "q6_k", "blk.25.ssm_conv1d": "q6_k", "blk.25.ssm_dt.bias": "q6_k", "blk.25.ssm_norm": "q6_k", "blk.25.ssm_out": "q6_k", "blk.26.attn_gate": "q6_k", "blk.26.attn_norm": "q6_k", "blk.26.attn_qkv": "q6_k", "blk.26.ffn_down": "q5_0", "blk.26.ffn_gate": "q4_0", "blk.26.ffn_up": "q4_0", "blk.26.post_attention_norm": "q6_k", "blk.26.ssm_a": "q6_k", "blk.26.ssm_alpha": "q6_k", "blk.26.ssm_beta": "q6_k", "blk.26.ssm_conv1d": "q6_k", "blk.26.ssm_dt.bias": "q6_k", "blk.26.ssm_norm": "q6_k", "blk.26.ssm_out": "q6_k", "blk.27.attn_k": "q6_k", "blk.27.attn_k_norm": "q6_k", "blk.27.attn_norm": "q6_k", "blk.27.attn_output": "q6_k", "blk.27.attn_q": "q6_k", "blk.27.attn_q_norm": "q6_k", "blk.27.attn_v": "q6_k", "blk.27.ffn_down": "q5_0", "blk.27.ffn_gate": "q4_0", "blk.27.ffn_up": "q4_0", "blk.27.post_attention_norm": "q6_k", "blk.28.attn_gate": "q6_k", "blk.28.attn_norm": "q6_k", "blk.28.attn_qkv": "q6_k", "blk.28.ffn_down": "q5_0", "blk.28.ffn_gate": "q4_0", "blk.28.ffn_up": "q4_0", "blk.28.post_attention_norm": "q6_k", "blk.28.ssm_a": "q6_k", "blk.28.ssm_alpha": "q6_k", "blk.28.ssm_beta": "q6_k", "blk.28.ssm_conv1d": "q6_k", "blk.28.ssm_dt.bias": "q6_k", "blk.28.ssm_norm": "q6_k", "blk.28.ssm_out": "q6_k", "blk.29.attn_gate": "q6_k", "blk.29.attn_norm": "q6_k", "blk.29.attn_qkv": "q6_k", "blk.29.ffn_down": "q5_0", "blk.29.ffn_gate": "q4_0", "blk.29.ffn_up": "q4_0", "blk.29.post_attention_norm": "q6_k", "blk.29.ssm_a": "q6_k", "blk.29.ssm_alpha": "q6_k", "blk.29.ssm_beta": "q6_k", "blk.29.ssm_conv1d": "q6_k", "blk.29.ssm_dt.bias": "q6_k", "blk.29.ssm_norm": "q6_k", "blk.29.ssm_out": "q6_k", "blk.30.attn_gate": "q6_k", "blk.30.attn_norm": "q6_k", "blk.30.attn_qkv": "q6_k", "blk.30.ffn_down": "q5_0", "blk.30.ffn_gate": "q4_0", "blk.30.ffn_up": "q4_0", "blk.30.post_attention_norm": "q6_k", "blk.30.ssm_a": "q6_k", "blk.30.ssm_alpha": "q6_k", "blk.30.ssm_beta": "q6_k", "blk.30.ssm_conv1d": "q6_k", "blk.30.ssm_dt.bias": "q6_k", "blk.30.ssm_norm": "q6_k", "blk.30.ssm_out": "q6_k", "blk.31.attn_k": "q6_k", "blk.31.attn_k_norm": "q6_k", "blk.31.attn_norm": "q6_k", "blk.31.attn_output": "q6_k", "blk.31.attn_q": "q6_k", "blk.31.attn_q_norm": "q6_k", "blk.31.attn_v": "q6_k", "blk.31.ffn_down": "q5_0", "blk.31.ffn_gate": "q4_0", "blk.31.ffn_up": "q4_0", "blk.31.post_attention_norm": "q6_k", "blk.32.attn_k": "q6_k", "blk.32.attn_k_norm": "q6_k", "blk.32.attn_norm": "q6_k", "blk.32.attn_output": "q6_k", "blk.32.attn_q": "q6_k", "blk.32.attn_q_norm": "q6_k", "blk.32.attn_v": "q6_k", "blk.32.ffn_down": "q5_0", "blk.32.ffn_gate": "q4_0", "blk.32.ffn_up": "q4_0", "blk.32.nextn.eh_proj": "q6_k", "blk.32.nextn.enorm": "q6_k", "blk.32.nextn.hnorm": "q6_k", "blk.32.nextn.shared_head_norm": "q6_k", "blk.32.post_attention_norm": "q6_k"}, "hist": {"q6_k": 343, "q5_0": 33, "q4_0": 66}}