Instructions to use continuum-ai/mixtral-8x7b-instruct-compacted-conservative with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use continuum-ai/mixtral-8x7b-instruct-compacted-conservative with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("continuum-ai/mixtral-8x7b-instruct-compacted-conservative")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

llama-cpp-python

How to use continuum-ai/mixtral-8x7b-instruct-compacted-conservative with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="continuum-ai/mixtral-8x7b-instruct-compacted-conservative",
	filename="mixtral-8x7b-compacted-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use continuum-ai/mixtral-8x7b-instruct-compacted-conservative with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf continuum-ai/mixtral-8x7b-instruct-compacted-conservative:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf continuum-ai/mixtral-8x7b-instruct-compacted-conservative:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf continuum-ai/mixtral-8x7b-instruct-compacted-conservative:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf continuum-ai/mixtral-8x7b-instruct-compacted-conservative: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 continuum-ai/mixtral-8x7b-instruct-compacted-conservative:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf continuum-ai/mixtral-8x7b-instruct-compacted-conservative: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 continuum-ai/mixtral-8x7b-instruct-compacted-conservative:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf continuum-ai/mixtral-8x7b-instruct-compacted-conservative:Q4_K_M

Use Docker

docker model run hf.co/continuum-ai/mixtral-8x7b-instruct-compacted-conservative:Q4_K_M

LM Studio
Jan

vLLM

How to use continuum-ai/mixtral-8x7b-instruct-compacted-conservative with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "continuum-ai/mixtral-8x7b-instruct-compacted-conservative"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "continuum-ai/mixtral-8x7b-instruct-compacted-conservative",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/continuum-ai/mixtral-8x7b-instruct-compacted-conservative:Q4_K_M

Ollama
How to use continuum-ai/mixtral-8x7b-instruct-compacted-conservative with Ollama:
```
ollama run hf.co/continuum-ai/mixtral-8x7b-instruct-compacted-conservative:Q4_K_M
```

Unsloth Studio new

How to use continuum-ai/mixtral-8x7b-instruct-compacted-conservative with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for continuum-ai/mixtral-8x7b-instruct-compacted-conservative to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for continuum-ai/mixtral-8x7b-instruct-compacted-conservative to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for continuum-ai/mixtral-8x7b-instruct-compacted-conservative to start chatting

MLX LM

How to use continuum-ai/mixtral-8x7b-instruct-compacted-conservative with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "continuum-ai/mixtral-8x7b-instruct-compacted-conservative"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "continuum-ai/mixtral-8x7b-instruct-compacted-conservative"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "continuum-ai/mixtral-8x7b-instruct-compacted-conservative",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use continuum-ai/mixtral-8x7b-instruct-compacted-conservative with Docker Model Runner:
```
docker model run hf.co/continuum-ai/mixtral-8x7b-instruct-compacted-conservative:Q4_K_M
```

Lemonade

How to use continuum-ai/mixtral-8x7b-instruct-compacted-conservative with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull continuum-ai/mixtral-8x7b-instruct-compacted-conservative:Q4_K_M

Run and chat with the model

lemonade run user.mixtral-8x7b-instruct-compacted-conservative-Q4_K_M

List all available models

lemonade list

mixtral-8x7b-instruct-compacted-conservative / README.md

EnricoFermi

fix: use hf.co (CORS-open) in verify URLs

8ec99b9 verified about 2 months ago

preview code

raw

history blame contribute delete

7.55 kB

metadata

tags:
  - 35b
  - android
  - apple-silicon
  - attested
  - chain-of-custody
  - consumer-gpu
  - cryptographically-verified
  - edge-inference
  - efficient
  - english
  - expert-pruning
  - forge-alloy
  - general
  - gguf
  - instruct
  - llama-cpp
  - lm-studio
  - local-inference
  - macbook
  - mixture-of-experts
  - mlx
  - mobile
  - moe
  - moe-compaction
  - multilingual
  - ollama
  - on-device
  - optimized
  - pruned
  - q4_k_m
  - quantized
  - raspberry-pi
  - reproducible
  - sparse-moe
  - text-generation
  - versatile
  - calibration-aware-pruning
  - mixtral
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
pipeline_tag: text-generation
license: apache-2.0

25% Experts Pruned, PPL 8.97 (base 8.14)

Mixtral-8x7B-Instruct-v0.1 compacted via calibration-aware MoE expert pruning (§4.1.3.4) against the unmodified source.

Perplexity: 8.97 (base 8.14, Δ +10.2%)
Compression: 93.4 GB → 20.4 GB Q4_K_M (4.6×)
Throughput: 142 tok/s generation, 437 tok/s prompt on RTX 5090

Every claim on this card is verified
Trust: self-attested · 1 benchmark · 1 device tested
ForgeAlloy chain of custody · Download alloy · Merkle-chained

A 93 GB datacenter MoE compressed to run on a MacBook Air. Forged from mistralai/Mixtral-8x7B-Instruct-v0.1 by removing the 2 least-activated experts per layer (8→6) via calibration-aware activation-frequency ranking on a held-out code corpus (300 examples, 148,945 tokens). Quantized to GGUF Q4_K_M for llama.cpp / Ollama / LM Studio. Apache-2.0. PPL 8.97 against the source's 8.14 (Δ +10.2%), evaluated via llama.cpp on wikitext-2-raw. Second row of the cross-family anchor table. Cryptographic provenance via ForgeAlloy.

Benchmarks

Benchmark	Score	Base	Δ	Verified
wikitext-2-raw PPL	8.97	8.14	+10.2%	✅ Result hash

What Changed (Base → Forged)

	Base	Forged	Delta
Perplexity	8.14	8.97	+10.2%
Experts / layer	8	6	−25% (2 removed per layer)
Total params	46.7B	~35B	−25%
Active params	12.9B	12.9B	Unchanged
Size (fp16)	93.4 GB	70.9 GB	−24%
Size (Q4_K_M)	—	20.4 GB	4.6× compression
Pipeline		expert-activation-profile → expert-prune → quant → eval	1 cycle

Runs On

Device	Format	Size	Speed
NVIDIA GeForce RTX 5090	Q4_K_M	20.4 GB	142 tok/s generation ✅ Verified
MacBook Pro 32GB	Q4_K_M	20.4 GB	Expected
MacBook Air 24GB	Q4_K_M	20.4 GB	Expected
RTX 3060 12GB+	Q4_K_M	20.4 GB	Expected (partial offload)
RTX 4090 24GB	Q4_K_M	20.4 GB	Expected
RTX 4090 24GB	fp16	70.9 GB	Expected (with offload)

Quick Start

# llama.cpp (any platform)
./llama-cli -m mixtral-8x7b-compacted-Q4_K_M.gguf \
  -p "Write a Python function that finds the longest palindromic substring." \
  -n 512 -ngl 99

# Ollama
ollama run continuum-ai/mixtral-8x7b-instruct-compacted-conservative

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "continuum-ai/mixtral-8x7b-instruct-compacted-conservative",
    torch_dtype="auto", device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(
    "continuum-ai/mixtral-8x7b-instruct-compacted-conservative"
)
inputs = tokenizer("def merge_sort(arr):", return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Methodology

Produced via §4.1.3.4 calibration-aware MoE expert activation count pruning. 300 held-out code examples (148,945 tokens) profiled across all 32 layers × 8 experts. The 2 least-activated experts per layer were removed. The surviving 6 experts per layer are the ones the model actually uses on the calibration domain.

Activation profile (sample layers):

Layer	Top experts	Bottom experts (removed)
Layer 0	5, 2, 3, 4, 0 (35K-49K)	1, 6 (~20K)
Layer 16	6, 2, 1, 5, 4 (37K-46K)	0, 3 (~20K)
Layer 31	3, 6, 5, 7, 0 (35K-54K)	1, 2 (~20K)

Full methodology in the sentinel-ai repository. The pipeline ran as expert-activation-profile → expert-prune → quant → eval on NVIDIA GeForce RTX 5090.

Cross-Family Anchor Table

Same §4.1.3.4 methodology across independently-trained model families.

Row	Model	Family	Experts	Kept	PPL	Status
1	qwen3-coder-30b-a3b	Qwen3 MoE	128	80	—	✅ Published
2	Mixtral 8x7B	Mixtral	8	6	8.97	✅ This model
3	Mixtral 8x22B	Mixtral	8	4	—	🔄 Forging now
4	Qwen3.5-35B-A3B	Qwen3.5	TBD	TBD	—	⬜ Planned
5	DeepSeek-V2-Lite	DeepSeek	64	32	—	⬜ Planned

Chain of Custody

Scan the QR or verify online. Download the alloy file to verify independently.

What	Proof
Model weights	`sha256:d7f65e31667d9b9bcfd8ca05e796df87bf8b6e59336a34f4703c9d3904e54bd8`
Alloy hash	`sha256:b26fd7adf36b7c8c`
Forged on	NVIDIA GeForce RTX 5090, 2026-04-10
Trust level	`self-attested`
Spec	ForgeAlloy — Rust/Python/TypeScript

Make Your Own

Forged with Continuum — a distributed AI world that runs on your hardware.

Continuum · Forge-Alloy · Sentinel-AI · Open-Eyes · Discord · Moltbook

Intelligence for everyone. Exploitation for no one.