Instructions to use Shockem/Qwen3.8-27b-Terse-Coder-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 Shockem/Qwen3.8-27b-Terse-Coder-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 Shockem/Qwen3.8-27b-Terse-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Shockem/Qwen3.8-27b-Terse-Coder-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Shockem/Qwen3.8-27b-Terse-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Shockem/Qwen3.8-27b-Terse-Coder-GGUF: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 Shockem/Qwen3.8-27b-Terse-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Shockem/Qwen3.8-27b-Terse-Coder-GGUF: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 Shockem/Qwen3.8-27b-Terse-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Shockem/Qwen3.8-27b-Terse-Coder-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Shockem/Qwen3.8-27b-Terse-Coder-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Shockem/Qwen3.8-27b-Terse-Coder-GGUF with Ollama:
```
ollama run hf.co/Shockem/Qwen3.8-27b-Terse-Coder-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Shockem/Qwen3.8-27b-Terse-Coder-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Shockem/Qwen3.8-27b-Terse-Coder-GGUF: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": "Shockem/Qwen3.8-27b-Terse-Coder-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Shockem/Qwen3.8-27b-Terse-Coder-GGUF with Docker Model Runner:
```
docker model run hf.co/Shockem/Qwen3.8-27b-Terse-Coder-GGUF:Q4_K_M
```

Lemonade

How to use Shockem/Qwen3.8-27b-Terse-Coder-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Shockem/Qwen3.8-27b-Terse-Coder-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-27b-Terse-Coder-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Shockem/Qwen3.8-27b-Terse-Coder-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 Shockem/Qwen3.8-27b-Terse-Coder-GGUF: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 Shockem/Qwen3.8-27b-Terse-Coder-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Shockem/Qwen3.8-27b-Terse-Coder-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Shockem/Qwen3.8-27b-Terse-Coder-GGUF: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 "Shockem/Qwen3.8-27b-Terse-Coder-GGUF: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"

Qwen3.8-27b-Terse-Coder-GGUF / README.md

Shockem

add Harness recommendations section (TB4-measured)

7602ead verified 8 days ago

preview code

Raw History Blame Contribute Delete

4.18 kB

	---
	license: apache-2.0
	base_model: Shockem/Qwen3.8-27b-Terse-Coder
	tags:
	- gguf
	- reasoning
	- coding
	- qwen3
	---

	# Qwen3.8-27b-Terse-Coder-GGUF

	GGUF builds of
	[Shockem/Qwen3.8-27b-Terse-Coder](https://huggingface.co/Shockem/Qwen3.8-27b-Terse-Coder)
	(round 8, final) — a fine-tune of
	[Qwen/Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B) with ~1/10 the
	chain-of-thought reasoning tokens on coding tasks and correctness preserved.

	Quant spread (Q4_K_M smoke-tested on llama.cpp — correct code generation,
	reasoning parsing, ~22 tok/s on 2× RTX 5060 Ti):

	\| File \| Size \| Notes \|
	\|---\|---\|---\|
	\| `Qwen3.8-27b-Terse-Coder.Q4_K_M.gguf` \| ~16.8G \| Balanced quality/speed — the default pick \|
	\| `Qwen3.8-27b-Terse-Coder.Q5_K_M.gguf` \| ~19.5G \| \|
	\| `Qwen3.8-27b-Terse-Coder.Q6_K.gguf` \| ~22.4G \| \|
	\| `Qwen3.8-27b-Terse-Coder.Q8_0.gguf` \| ~29.0G \| Near-lossless \|
	\| `Qwen3.8-27b-Terse-Coder.mmproj-f16.gguf` \| ~0.9G \| Vision projector (required for images) \|
	\| `Qwen3.8-27b-Terse-Coder.mmproj-Q8_0.gguf` \| ~0.6G \| Vision projector, quantized \|

	Usage (llama.cpp server):
	Chat template: use [Shockem/froggeric-terse-coder](https://huggingface.co/Shockem/froggeric-terse-coder) (based on [froggeric/Qwen-Fixed-Chat-Templates](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates)) (also bundled here as `chat_template.jinja`) — it carries the anti-rumination tool rules the model was evaluated with; serving without it changes agentic behavior.


	```bash
	llama-server -m Qwen3.8-27b-Terse-Coder.Q4_K_M.gguf \
	--mmproj Qwen3.8-27b-Terse-Coder.mmproj-f16.gguf \
	-ngl 99 -c 32768
	```

	The MTP draft layer is included in the GGUF but unused by llama.cpp
	(harmless warnings about unused `blk.N.nextn.*` tensors are expected);
	speculative decoding is a vLLM-side feature. Behavior/quality reference:
	HE+ 91.5 / MBPP+ 79.4 / GSM8K 98.5 / GPQA 79.8 on the source repo (vLLM
	measurements; GGUF Q4_K_M verified by smoke test only — validate quality on
	your own hardware before relying on it).


	## Harness recommendations

	How you drive the model matters as much as which build you run. Measured on
	Terminal-Bench 4.0 (Sep 2026, local vLLM serving): prompt-level guardrails
	did not reduce token burn or stop grinding — the dominant cost was the
	harness re-sending the full transcript every step. Zero tool-call loops
	observed in any trajectory.

	- Let the server own sampling — omit temperature/top_p/top_k; the
	checkpoint config applies temp 0.6 / top_k 20 / top_p 0.95 /
	repetition_penalty 1.05. Never send `min_p` (vLLM rejects it under MTP
	spec decode).
	- Serve with the bundled chat template (`chat_template.jinja`; also at
	[Shockem/froggeric-terse-coder](https://huggingface.co/Shockem/froggeric-terse-coder)).
	The anti-rumination rules inject even alongside custom system prompts —
	bypassing the template (bare completions API, client-side template) is the
	"repeats already-done steps" failure mode.
	- Per-turn max_tokens 4–8k is generous (routine coding answers are
	25–150 tokens; thinks median ~38). Use 49152 only as a session floor for
	agents, not a per-turn target.
	- Context management is the biggest lever. Keep ~3 recent tool results,
	cap older blobs at ~4k chars. Unbounded agent history was worth ~270k+
	input tokens per task in our probe — that is a harness property, not a
	model property.
	- Think text arrives in `reasoning_content` — empty `content` with
	non-empty `reasoning_content` is a normal turn, not an error.
	- Raise `reasoning_effort` for genuinely hard problems — the model still
	scales deliberation up when the problem needs it (GPQA median ~900
	reasoning tokens); terseness targets waste, not deliberation.

	Source and provenance: fp16 merge at
	[Shockem/Qwen3.8-27b-Terse-Coder](https://huggingface.co/Shockem/Qwen3.8-27b-Terse-Coder);
	vLLM deployment build at
	[Shockem/Qwen3.8-27b-Terse-Coder-NVFP4](https://huggingface.co/Shockem/Qwen3.8-27b-Terse-Coder-NVFP4);
	adapter lineage at
	[Shockem/Qwen3.8-27b-Terse-Coder-LoRA](https://huggingface.co/Shockem/Qwen3.8-27b-Terse-Coder-LoRA).
	Licensed Apache 2.0, same as the base model (© Qwen Team, Alibaba Cloud).