Instructions to use Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF with Trellis:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-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 Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S
# Run inference directly in the terminal:
llama cli -hf Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S
# Run inference directly in the terminal:
llama cli -hf Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S

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 Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S
# Run inference directly in the terminal:
./llama-cli -hf Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S

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 Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S

Use Docker

docker model run hf.co/Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S

LM Studio
Jan

vLLM

How to use Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-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": "Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S

Ollama
How to use Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF with Ollama:
```
ollama run hf.co/Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S
```
Unsloth Desktop

How to use Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S

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": "Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF with Docker Model Runner:
```
docker model run hf.co/Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S
```

Lemonade

How to use Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S

Run and chat with the model

lemonade run user.MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF-IQ3_S

List all available models

lemonade list

Hermes Agent

How to use Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-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 Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S

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 Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S

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 "Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF:IQ3_S" \
  --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"

MODEL CARD INCOMPLETE

BENCHMARKS PENDING

!!! quantized for use with ik_llama.cpp and its derivatives !!!

!!! incompatible with mainline llama.cpp as of commit #34af94c !!!

What's that?

An experimental, English-roleplay-oriented, ik_llama.cpp-only MuXodious/GLM-4.7-Flash-absolute-heresy quantization for users who want an IQ3_M-sized file but prefer to spend precision on MLA, routing, shared experts, and output-sensitive tensors.

Rationale

I wanted a quant that would fit my GPU with some context and minimal offload. Simple as.
This gguf was made to compete with IQ3_M/IQ4_XS by compressing sparse expert ffn tensors in SOTA low-bit quant types (IQ3_KT/IQ4_KT) while protecting the most compression-sensitive, architecture critical tensors. I had concerns with mainline quant method compromises - such as shared experts in 3-bit, and the MLA KV "condensation" weights (attn_kv_a_mqa) being quanted lower than attn_k_b (the layer extracting Keys from the shared latent attention vector). Fearing that overcompressed MLA latent projection would mangle reconstructed attention states, I went for a much higher quantization for these. The recipe provided is, however, an exploratory MLA/MoE allocation, not gospel.
The proportion of ffn_exps parameters in the entire model is 92.46%. And 2.12% for lm_head and embeddings. Meaning EVERYTHING else - the shared exps, the attention tensors - is 3 GB in bf16. These also happen to be quantization sensitive tensors. As a prime example, keeping expert routing weights in bf16 across the entire gguf has cost... 7.5 MB over IQ3_S.

The imatrix was generated on wrapped natural language english text from eaddario/imatrix-calibration, using kld-sweep-dataset by cmhamiche. The imatrix was not calibrated for STEM, mathematics, code, or non-English languages. I was building it for my use purposes.
However, I'm not opposed to making a trellis quant for other use cases if anyone needs it.

UPD: since the IQ3_KT ffn_down_exps also seems to be perfectly functional, it's provided as well.

Mixed Trellis

Component / Role	Tensor (Layer)	Dense Block 0 (1x)	MoE/MLA Blocks (46x)
Global Layers	`token_embd.weight` `output.weight`	iq5_k —	— iq6_k
MLA Compressed	`attn_q_a.weight` `attn_kv_a_mqa.weight`	bf16 bf16	bf16 bf16
MLA Attention	`attn_q_b` `attn_k_b` / `attn_v_b` `attn_output.weight`	q8_0 q8_0 q8_0	q8_0 q8_0 iq6_k
MoE Routing	`ffn_gate_inp.weight` `exp_probs_b`	— —	bf16 f32
MoE Experts	`ffn_down_exps.weight` `ffn_gate_exps.weight` `ffn_up_exps.weight`	— — —	iq4_kt iq3_kt iq3_kt
Shared Experts	`ffn_down_shexp` `ffn_gate_shexp` `ffn_up_shexp`	— — —	q8_0 q8_0 q8_0
Dense MLP	`ffn_down` / `ffn_gate` / `ffn_up`	q8_0	—

IQ3_KT

Component / Role	Tensor (Layer)	Dense Block 0 (1x)	MoE/MLA Blocks (46x)
Global Layers	`token_embd.weight` `output.weight`	iq5_k —	— iq6_k
MLA Compressed	`attn_q_a.weight` `attn_kv_a_mqa.weight`	bf16 bf16	bf16 bf16
MLA Attention	`attn_q_b` `attn_k_b` / `attn_v_b` `attn_output.weight`	q8_0 q8_0 q8_0	q8_0 q8_0 iq6_k
MoE Routing	`ffn_gate_inp.weight` `exp_probs_b`	— —	bf16 f32
MoE Experts	`ffn_down_exps.weight` `ffn_gate_exps.weight` `ffn_up_exps.weight`	— — —	iq3_kt iq3_kt iq3_kt
Shared Experts	`ffn_down_shexp` `ffn_gate_shexp` `ffn_up_shexp`	— — —	q8_0 q8_0 q8_0

Cheers

Z.ai - the base model.
ikawrakow and contributors of ik_llama.cpp - I probably misused your creation.
MuXodious - for letting the model swear.
cmhamiche - for accessible, ready-to-use dataset construction tool.
eaddario - for the imatrix dataset.

Downloads last month: 541

GGUF

Model size

30B params

Architecture

deepseek2

Hardware compatibility

3-bit

Model tree for Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF

Base model

zai-org/GLM-4.7-Flash

Finetuned

MuXodious/GLM-4.7-Flash-absolute-heresy

Quantized

(6)

this model

Koshkasa
/

MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF

MODEL CARD INCOMPLETE

BENCHMARKS PENDING

What's that?

Rationale

Mixed Trellis

IQ3_KT

Cheers

Model tree for Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF

Dataset used to train Koshkasa/MuXodious_GLM-4.7-Flash-absolute-heresy-mixed-trellis-GGUF