iapp/ openthai2.0-qwen3.8-27b

26 Downloads Updated 6 days ago

OpenThai2.0 - Best All-in-One Opensource Thai Knowledge, Document, and Agentic AI

vision tools thinking

ollama run iapp/openthai2.0-qwen3.8-27b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "iapp/openthai2.0-qwen3.8-27b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='iapp/openthai2.0-qwen3.8-27b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'iapp/openthai2.0-qwen3.8-27b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model iapp/openthai2.0-qwen3.8-27b

OpenCode

OpenCode ollama launch opencode --model iapp/openthai2.0-qwen3.8-27b

Hermes Agent

Hermes Agent ollama launch hermes --model iapp/openthai2.0-qwen3.8-27b

OpenClaw

OpenClaw ollama launch openclaw --model iapp/openthai2.0-qwen3.8-27b

Models

Name

1 model

Size / Usage

Context

Input

openthai2.0-qwen3.8-27b:latest

18GB · 256K context window · Text, Image · 6 days ago

openthai2.0-qwen3.8-27b:latest

18GB

256K

Text, Image

Readme

OpenThai2.0 - Opensource Thai Knowledge, Document, and Agentic AI (GGUF)

ollama run iapp/openthai2.0-qwen3.8-27b

GGUF quantizations of openthai2.0-qwen3.8-27b (v9) for llama.cpp. Includes the MTP head (exported as nextn layers) and the vision projector.

file	size	use
openthai2.0-qwen3.8-27b-Q4_K_M.gguf	~17 GB	recommended balance
openthai2.0-qwen3.8-27b-IQ2_M.gguf	~9.8 GB	recommended 2-bit — imatrix-calibrated (Thai+EN); passes factual sanity checks that plain Q2_K fails
openthai2.0-qwen3.8-27b-Q2_K.gguf	~11 GB	plain 2-bit — ⚠️ factual slips observed; prefer IQ2_M
openthai2.0-qwen3.8-27b-Q8_0.gguf	~29 GB	near-lossless
mmproj-openthai2.0-qwen3.8-27b-F16.gguf	—	vision projector (documents/images)

Run

llama-server -m openthai2.0-qwen3.8-27b-Q4_K_M.gguf       --mmproj mmproj-openthai2.0-qwen3.8-27b-F16.gguf -c 32768

⚠️ The model reasons before it answers. Use a large context (32k) and leave max_tokens unset or >= 8192, or replies may come back empty.

Sanity-verified: Q4_K_M (CPU) and IQ2_M (GPU) answer Thai factual prompts correctly; imatrix-a80.dat is included for community re-quants. Full benchmarks and model card: see the main bf16 repo.

# OpenThai2.0 - Opensource Thai Knowledge, Document, and Agentic AI (GGUF)

```
ollama run iapp/openthai2.0-qwen3.8-27b
```

GGUF quantizations of [openthai2.0-qwen3.8-27b](https://huggingface.co/iapp/openthai2.0-qwen3.8-27b) (v9)
for llama.cpp. **Includes the MTP head** (exported as nextn layers) and the vision projector.

| file | size | use |
|---|---|---|
| openthai2.0-qwen3.8-27b-Q4_K_M.gguf | ~17 GB | recommended balance |
| openthai2.0-qwen3.8-27b-IQ2_M.gguf | ~9.8 GB | **recommended 2-bit** — imatrix-calibrated (Thai+EN); passes factual sanity checks that plain Q2_K fails |
| openthai2.0-qwen3.8-27b-Q2_K.gguf | ~11 GB | plain 2-bit — ⚠️ factual slips observed; prefer IQ2_M |
| openthai2.0-qwen3.8-27b-Q8_0.gguf | ~29 GB | near-lossless |
| mmproj-openthai2.0-qwen3.8-27b-F16.gguf | — | vision projector (documents/images) |

## Run

llama-server -m openthai2.0-qwen3.8-27b-Q4_K_M.gguf       --mmproj mmproj-openthai2.0-qwen3.8-27b-F16.gguf -c 32768

> ⚠️ The model reasons before it answers. Use a large context (32k) and leave max_tokens
> unset or >= 8192, or replies may come back empty.

Sanity-verified: Q4_K_M (CPU) and IQ2_M (GPU) answer Thai factual prompts correctly; imatrix-a80.dat is included for community re-quants.
Full benchmarks and model card: see the main bf16 repo.

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)