Instructions to use islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-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 islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-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 islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF: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 islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF: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 islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF:IQ4_XS

Use Docker

docker model run hf.co/islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF:IQ4_XS

LM Studio
Jan

vLLM

How to use islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF:IQ4_XS

Ollama
How to use islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF with Ollama:
```
ollama run hf.co/islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF:IQ4_XS
```
Unsloth Desktop

How to use islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF: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": "islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF with Docker Model Runner:
```
docker model run hf.co/islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF:IQ4_XS
```

Lemonade

How to use islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF:IQ4_XS

Run and chat with the model

lemonade run user.Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF-IQ4_XS

List all available models

lemonade list

Hermes Agent

How to use islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-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 islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF: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 islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF:IQ4_XS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF: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 "islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF: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"

Qwen3.8-27B ByteShape IQ4_XS-3.84bpw — ASCII-P1M vocab

ByteShape's Qwen3.8-27B IQ4_XS-3.84bpw (ShapeLearn per-tensor quantization) with its vocabulary pruned to ASCII plus math/typography symbols, using bsaleh03/ASCII-Condensed-prune-tools (--policy P1M).

English and code only. See Limitations.


File	`Qwen3.8-27B-ByteShape-IQ4_XS-3.84bpw-ASCII-P1M.gguf`
Size	12.25 GB (source 13.08 GB)
Vocab	129,272 tokens (source 248,320)
sha256	`d533c568ba028fb7bc24d646d9f0259341a388fb2535e559fd0bc62275a55a4d`
Source sha256	`89434f23dc89c5f990894e3fe9fdad19d88c370f0d3638a176f29933f218b78b`
Architecture	`qwen35` (hybrid Gated DeltaNet + attention), 65 blocks, MTP head kept
Parameters	Qwen3.8-27B (27.3B). The Hub shows 26.1B because it counts tensor shapes, and the pruned vocab removes 119,048 rows from both `token_embd` and `output` (~1.22B parameters). Every transformer weight is unchanged.

What changed

Only token_embd.weight (IQ4_XS, 0.675 → 0.352 GB) and output.weight (Q6_K, 1.043 → 0.543 GB) were touched. Rows are gathered in quantized space: no dequantize/requantize, so every kept row is bit-identical to the source. The tokenizer arrays and merges were rewritten and the special-token ids remapped. The 256 byte-fallback tokens, all specials and all partial-UTF-8 fragments are kept, so any text can still be tokenized.

verify_prune.py --policy P1M passed every check:

all 864 non-vocab tensors byte-identical to the source
sampled vocab rows identical to their source rows
metadata preserved
kept set exactly what P1M specifies

Tool commit: 376a426d5c6b30f28e03c6efaa9edcf85048773f.

Measurements

Measured on an RTX 5060 Ti 16 GB with llama.cpp v0.4.1.

Perplexity: ctx 4096, 30 chunks, f16 KV. Lower is better, and the figures are deterministic, so they compare exactly across rows.

model	code (mixed TS/JS project source)	code, ASCII-only lines	wikitext-2
ByteShape IQ4_XS-3.84bpw (source)	1.6671	1.6490	5.9480
this file	1.7156	1.6488	5.9612
Unsloth UD-IQ4_XS (reference)	1.6583	—	5.8322

On ASCII-only text the prune costs nothing (1.6488 vs 1.6490). The +2.9% on the mixed code corpus comes entirely from its 1.27% non-ASCII characters, mostly Bangla string literals.

Context and speed: whole model on GPU, q4_0 KV cache, -ub 512, MTP off.

ctx	VRAM allocated	prefill	decode
96k	13,952 MiB	939 t/s	28.7 t/s
128k	14,391 MiB	939 t/s	28.8 t/s
160k	14,873 MiB	895 t/s	27.7 t/s

A 16 GB card with a light desktop fits about 128k of context; 160k needs a nearly idle desktop.

Agentic coding eval (10 executable tasks, thinking on, temp 1.0 / top_p 0.95 / top_k 20): 8/10, 18,381 tokens total. One of the two failures is a grading artifact: the answer ended with a usage-example code block, which the grader took for the solution.

Tool calling and mid-conversation system messages work with a patched chat template (see below).

Usage

llama-server -m Qwen3.8-27B-ByteShape-IQ4_XS-3.84bpw-ASCII-P1M.gguf \
  -c 131072 -ngl 99 -fa on --cache-type-k q4_0 --cache-type-v q4_0 \
  --jinja --temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.0

MTP: the head is still in the file; add --spec-type draft-mtp --spec-draft-n-max 2 if you have the VRAM for the draft context.
Claude Code and similar agents: the stock Qwen3.8 template raises System message must be at the beginning. on mid-conversation system messages. Patch that branch to render them as normal system blocks.

Limitations

Non-Latin text breaks. Scripts outside ASCII and the P1M symbol set (Bangla, CJK, Arabic, Cyrillic, …) fall back to one token per UTF-8 byte. The model was never trained on those byte sequences, so it reads them as garbled text. A Bangla prompt got a romanized reply saying the input looked garbled; the full-vocab model answers it correctly. For multilingual use, take the source file instead.
Accented Latin (é, ü, ñ) is not in P1M either, so it also degrades.
Not affiliated with ByteShape or the Qwen team. All numbers above come from one machine.

Credits

Base model: Qwen/Qwen3.8-27B (Apache-2.0)
Quantization: ByteShape (ShapeLearn)
Vocab pruning: bsaleh03/ASCII-Condensed-prune-tools

Downloads last month: 997

GGUF

Model size

26B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for islamsidratul/Qwen3.8-27B-ByteShape-IQ4_XS-ASCII-GGUF

Base model

Qwen/Qwen3.8-27B

Quantized

byteshape/Qwen3.8-27B-GGUF

Quantized

(1)

this model