Instructions to use mcham/Qwen3.8-27B-padthai-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use mcham/Qwen3.8-27B-padthai-gguf 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 mcham/Qwen3.8-27B-padthai-gguf:IQ2_M
# Run inference directly in the terminal:
llama cli -hf mcham/Qwen3.8-27B-padthai-gguf:IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mcham/Qwen3.8-27B-padthai-gguf:IQ2_M
# Run inference directly in the terminal:
llama cli -hf mcham/Qwen3.8-27B-padthai-gguf:IQ2_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 mcham/Qwen3.8-27B-padthai-gguf:IQ2_M
# Run inference directly in the terminal:
./llama-cli -hf mcham/Qwen3.8-27B-padthai-gguf:IQ2_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 mcham/Qwen3.8-27B-padthai-gguf:IQ2_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mcham/Qwen3.8-27B-padthai-gguf:IQ2_M

Use Docker

docker model run hf.co/mcham/Qwen3.8-27B-padthai-gguf:IQ2_M

LM Studio
Jan
Ollama
How to use mcham/Qwen3.8-27B-padthai-gguf with Ollama:
```
ollama run hf.co/mcham/Qwen3.8-27B-padthai-gguf:IQ2_M
```
Unsloth Desktop

How to use mcham/Qwen3.8-27B-padthai-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mcham/Qwen3.8-27B-padthai-gguf:IQ2_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": "mcham/Qwen3.8-27B-padthai-gguf:IQ2_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mcham/Qwen3.8-27B-padthai-gguf with Docker Model Runner:
```
docker model run hf.co/mcham/Qwen3.8-27B-padthai-gguf:IQ2_M
```

Lemonade

How to use mcham/Qwen3.8-27B-padthai-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mcham/Qwen3.8-27B-padthai-gguf:IQ2_M

Run and chat with the model

lemonade run user.Qwen3.8-27B-padthai-gguf-IQ2_M

List all available models

lemonade list

Hermes Agent

How to use mcham/Qwen3.8-27B-padthai-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mcham/Qwen3.8-27B-padthai-gguf:IQ2_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 mcham/Qwen3.8-27B-padthai-gguf:IQ2_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mcham/Qwen3.8-27B-padthai-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mcham/Qwen3.8-27B-padthai-gguf:IQ2_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 "mcham/Qwen3.8-27B-padthai-gguf:IQ2_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"

What is this model?

This model is intended to strip all other unused languaged and only support Thai, English.

By using generated iMatrix data, I have managed to keep good part of this model and only using 2-4 bit range.

The quant used are mostly IQ quants, this will compress better with provided IMatrix.

Who is it for?

By design the model is is around 8GB to 10GB that will fit A GPU size of 12GB much better.

Smallest Quant IQ2_M with 64K Context at Q4_1 will comsume around 11.6GB of VRAM.

What was calibrated using iMatrix?

Tool, Math, Code and Language
Language calibration: Thai, English

What quantization provided:

Quant	Size	Mixture	Recommendation
IQ3_XS	10.517 GiB (3.307 BPW)	Q8_0,Q6_K,IQ4_XS,IQ3_S,IQ3_S,IQ2_S	Solid embd/output, Good Math/Tool Use
IQ3_XXS_F	10.08 GiB (3.17 BPW)	IQ4_XS,IQ3_S,IQ3_XXS,IQ2_S,IQ2_XS	Fast, avg Math/Tool Use
IQ3_XXS	9.488 GiB (2.983 BPW)	Q8_0,Q6_K,IQ4_XS,IQ3_XXS,IQ2_XS	Solid embd/output, Reduced ffn,attn
IQ2_M	8.564 GiB (2.693 BPW)	IQ4_XS,IQ3_XXS,IQ2_XXS	Fast, Slightly inaccurate serious use

Side Models provided:

MTP is quantized generic from gglm. So Speed will gain mostly on non-Thai Prompts.

MMPROJ is Quantized from Official Qwen3.8-27B, this will save and speed up your use.

Type	Quant	Size
MTP	IQ4_M	1607.38 MiB (4.54 BPW)
MMRPOJ	Q8_0	601 MiB
IMATRIX	-	14 MiB

Recommendation:

IQ2_M/IQ3_XS_F Will gain the best speed when using ik_llama --repack

GGUF-Bench

bfcl: tool and agentic use capability

bigcodebench: coding capability

musr: reasoning

Quant	bfcl	bigcodebench	musr
UD-Q4_K_M	0.708	0.604	0.72
UD-IQ3_XXS	0.687	0.599	0.724
IQ3_XS	0.693	0.567	0.716
IQ3_XXS_F	0.669	0.588	0.668
IQ3_XXS	0.681	0.537	0.644
IQ2_M	0.615	0.408	0.672

Example Runs:

Use Temp settings same as unsloth's.

Use MTP with Ngram-Mod to speed up yout TG and PP.

If you build llama with CUDA you can mix differnt KV quants using -DGGML_CUDA_FA_ALL_QUANTS.

llama-server \
    -t 4 -dev CUDA0,CUDA1 \
    --reasoning off --reasoning-budget 0 --reasoning-format deepseek \
    --temp 0.7 --top-p 0.8 --top-k 20 --presence-penalty 1.5 --min-p 0.0 \
    -b 4096 -ub 2048 \
    --jinja --alias Qwen/Qwen3.8-27B -sm tensor \
    -m Qwen3.8-27B-padthai-IQ2_M.gguf \
    -mm mmproj-Q8_0.gguf \
    -md mtp-Qwen3.8-27B-padthai-IQ4_XS.gguf \
    --spec-type draft-mtp,ngram-mod --spec-draft-n-max 2 --spec-ngram-mod-n-match 24 --spec-ngram-mod-n-min 0 --spec-ngram-mod-n-max 128  \
    -c 64000 -ctk q8_0 -ctv q5_1 -ngl 99 -ngld 99 \
    --cache-ram 1000 \
    -ts 1,1 -fa on -fit off \
    --host 0.0.0.0 --timeout 3600

Downloads last month: 2,157

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

View +1 variant

Inference Providers NEW

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

Model tree for mcham/Qwen3.8-27B-padthai-gguf

Base model

Qwen/Qwen3.8-27B

Quantized

unsloth/Qwen3.8-27B-GGUF

Quantized

(21)

this model

mcham
/

Qwen3.8-27B-padthai-gguf

What is this model?

Who is it for?

What was calibrated using iMatrix?

What quantization provided:

Side Models provided:

Recommendation:

GGUF-Bench

Example Runs:

Model tree for mcham/Qwen3.8-27B-padthai-gguf

Dataset used to train mcham/Qwen3.8-27B-padthai-gguf

Space using mcham/Qwen3.8-27B-padthai-gguf 1