Instructions to use WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-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 WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-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 WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF
# Run inference directly in the terminal:
llama cli -hf WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF
# Run inference directly in the terminal:
llama cli -hf WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF

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 WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF
# Run inference directly in the terminal:
./llama-cli -hf WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF

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 WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF

Use Docker

docker model run hf.co/WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF

LM Studio
Jan
Ollama
How to use WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF with Ollama:
```
ollama run hf.co/WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF
```
Unsloth Desktop

How to use WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF

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": "WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF with Docker Model Runner:
```
docker model run hf.co/WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF
```

Lemonade

How to use WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF

Run and chat with the model

lemonade run user.DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-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 WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF

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 WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF

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 "WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF" \
  --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"

Line status (2026-08-12): use with caution. This first-generation REAM release passed its structural and smoke checks at publication time, but the cascaded descendants built from it (REAM128, REAM96) later showed severe multi-turn degradation, and the whole REAM line is being rebuilt with a revised methodology (single-step prune-first from the base model, longer multi-turn calibration). A REAM144 replacement targeting the same memory tier is planned; this repo may be superseded.

DeepSeek V4 Flash 0731 REAM160-180B DS4 Q2

⚠️ This checkpoint requires a patched inference engine. The upstream antirez/ds4 does not recognize the 160-expert topology.

Fork: https://github.com/iamwavecut/ds4

This is a 2-bit DS4-specific GGUF of the REAM160 variant of DeepSeek V4 Flash. REAM160 reduces the routed-expert count from 256 to 160 via calibration-guided, training-free expert merge, then quantizes to IQ2_XXS / Q2_K for routed tensors and Q8 for attention, shared experts, and output projections.

Quantization layout

Routed gate/up: IQ2_XXS.
Routed down: Q2_K.
Attention projections, shared experts, and output: Q8.
MTP and DSpark tensors and metadata are absent.
File size: 53.4 GiB.

Native REAM and quantization methodology

REAM160 is a calibration-guided, training-free expert merge: it does not apply gradient updates or add training examples to the checkpoint.

Calibration composition: 3,072 samples × 512 tokens.

Slice	Samples	Share	Pinned sources and focus
Code	614	20.0%	`sahil2801/CodeAlpaca-20k` and `bigcode/self-oss-instruct-sc2-exec-filter-50k`; instruction following and executable code
Math	307	10.0%	`openai/gsm8k` and `AI-MO/NuminaMath-CoT`; arithmetic and mathematical reasoning
Agent/tool	1,075	35.0%	`NousResearch/hermes-function-calling-v1`; function selection and structured tool calls
Russian/Cyrillic	1,076	35.0%	`ZeroAgency/ru-big-russian-dataset`; Russian and Cyrillic language coverage

A disjoint 512-sample heldout split was excluded from calibration.

At each layer, REAP saliency is the routed activation norm multiplied by router probability. The 160 highest-saliency source experts become centroids; the remaining source experts are assigned by their mean output and router-gate similarity, with group capacity 32. Each group is merged by saliency-weighted deterministic FP32 accumulation, router rows are remapped, and top-k 6 routing is preserved. Calibration therefore determines which source experts are retained and combined for the code, math, agent/tool, and Russian/Cyrillic workload mix; it is not fine-tuning.

The DS4 importance matrix reuses the exact REAM160 calibration activations with the packed-expert mapping. Quantization consumes it with --imatrix and --imatrix-strict: routed gate/up tensors use IQ2_XXS, routed down tensors use Q2_K, and attention projections, shared experts, and output use Q8. Conversion is direct from Safetensors to GGUF without an intermediate F16 checkpoint.

Usage

Clone the fork and build:

git clone https://github.com/iamwavecut/ds4
cd ds4
make

Full residency (requires ≥56 GiB GPU wired memory on macOS):

sudo sysctl iogpu.wired_limit_mb=62976
./ds4 -m DeepSeek-V4-Flash-0731-REAM160-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-chat-v2-imatrix.gguf \
      --nothink

SSD streaming (for machines that cannot hold the full 53.4 GiB model):

./ds4 -m DeepSeek-V4-Flash-0731-REAM160-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-chat-v2-imatrix.gguf \
      --nothink --ssd-streaming

--nothink selects bounded direct replies. Remove it only when enabling thinking with a completion budget suitable for longer reasoning.

This is a DS4-specific GGUF, not a generic llama.cpp or Transformers artifact.

Measured quality

Comparative heldout NLL/PPL: not measured yet.
DS4 continuation suite: 100/100 pass.
Quantization and validation wall time: 9.304 hours.

Semantic request modes: direct=75, thinking=25.

Performance benchmarks

Hardware: Apple M2 Max, 64 GB unified memory, macOS, Metal backend. Full model residency (53.4 GiB mapped), iogpu.wired_limit_mb=62976. Greedy decoding (--temp 0 --seed 42 --nothink), 128 generated tokens, 10 runs per context size, prompts padded to ~70% of context.

Context	Prompt size	Prefill t/s (median)	Generation t/s (median)
4K	~2K tok	214.37	19.02
8K	~5K tok	184.15	11.45
16K	~10K tok	131.62	10.32
32K	~22K tok	153.99	9.56

Detailed per-run statistics:

Context	Runs	Prefill avg	Prefill min–max	Gen avg	Gen min–max
4K	10	211.33	175.70–236.50	18.87	15.96–20.86
8K	10	183.13	159.51–197.52	10.60	3.27–13.51
16K	10	130.86	90.48–161.60	8.63	2.59–11.03
32K	10	150.38	128.17–162.35	8.19	2.45–10.71

SSD streaming mode (same hardware, for comparison): ~6–7 t/s prefill, ~8–9 t/s generation at 4K context.

License

MIT License — same as the upstream DeepSeek-V4 weights.

Downloads last month: 624

GGUF

Model size

180B params

Architecture

deepseek4

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B-DS4-GGUF

Base model

deepseek-ai/DeepSeek-V4-Flash-0731

Quantized

WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B

Quantized

(2)

this model