Instructions to use Baekpica/Solar-Open2-250B-Mixed-Quant-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 Baekpica/Solar-Open2-250B-Mixed-Quant-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 Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF
# Run inference directly in the terminal:
llama cli -hf Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF
# Run inference directly in the terminal:
llama cli -hf Baekpica/Solar-Open2-250B-Mixed-Quant-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 Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF
# Run inference directly in the terminal:
./llama-cli -hf Baekpica/Solar-Open2-250B-Mixed-Quant-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 Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Use Docker

docker model run hf.co/Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

LM Studio
Jan

vLLM

How to use Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Baekpica/Solar-Open2-250B-Mixed-Quant-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": "Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Ollama
How to use Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF with Ollama:
```
ollama run hf.co/Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF
```
Unsloth Desktop

How to use Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Baekpica/Solar-Open2-250B-Mixed-Quant-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": "Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF with Docker Model Runner:
```
docker model run hf.co/Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF
```

Lemonade

How to use Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Run and chat with the model

lemonade run user.Solar-Open2-250B-Mixed-Quant-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Baekpica/Solar-Open2-250B-Mixed-Quant-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 Baekpica/Solar-Open2-250B-Mixed-Quant-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 Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Baekpica/Solar-Open2-250B-Mixed-Quant-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Baekpica/Solar-Open2-250B-Mixed-Quant-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 "Baekpica/Solar-Open2-250B-Mixed-Quant-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"

Solar Open2 250B Mixed-Quant GGUF

Built with Solar.

This repository contains the locked MXQ-v1 candidate derived from upstage/Solar-Open2-250B. It preserves the complete topology: 48 layers, all 320 routed experts per layer, one shared expert, and the original [GQA, KDA, KDA, KDA] × 12 schedule. No expert, layer, or parameter pruning, merging, or distillation was performed. This is an independent conversion and is not an official Upstage release.

Support my work

I work on making large language models practical on hardware they were never really designed to fit on — through mixed quantization, inference optimization, custom kernels, and serving experiments.

While much of the development happens on local hardware, calibration, profiling, and large-scale validation often require expensive on-demand GPUs.

Contributions help pay for that compute, storage, and testing infrastructure, so I can keep experimenting and publishing the results openly.

Artifact

Variant	Split	Size	Approximate BPW
MXQ-v1	11 shards	95,533,532,160 bytes (88.973 GiB)	3.05

Download the complete 11-file split beginning with Solar-Open2-250B-MXQ-v1-00001-of-00011.gguf. Exact hashes are in MXQ-v1-SHA256SUMS.

The full BF16 and full-model Q8_0 reference conversions are published separately in Baekpica/Solar-Open2-250B-GGUF.

Precision recipe

Module family	Precision
Token embedding, LM head	Q8_0
GQA q/k/v/o/g projections	Q8_0
KDA matrix projections	Q8_0
Shared expert gate/up/down	Q8_0
Routed gate/up, layers 4–43	IQ2_XXS + imatrix
Routed down, layers 4–43	Q3_K + imatrix
Routed gate/up/down, layers 0–3 and 44–47	Q4_K + imatrix
Router, norms, small KDA control/norm/conv tensors	F32

The final GGUF contains 1,083 tensors: 409 F32, 530 Q8_0, 80 IQ2_XXS, 40 Q3_K, and 24 Q4_K tensors. quant-recipe-v1.yaml and verify-v1.json contain the machine-readable recipe and verification result.

Calibration

The Solar chat-template calibration corpus follows the published mix from Baekpica/Solar-Open2-120B-A15B-REAM-148E-Healing-Mix: instruction chat 22%, Cascade stage-1 reasoning 16%, Cascade stage-2 reasoning 16%, Korean 16%, other multilingual 12%, finance 6%, SWE 6%, and algorithmic code 6%.

The imatrix processed 590 × 512-token chunks. Layers 1–47 reached strict 320/320 routed-expert coverage. Layer 0 retained one explicit, pinned exception of 29 zero-activation experts; the exact IDs and gate are recorded in verify-imatrix.json. No precision was lowered to compensate for this exception.

Validation status

All 11 shards passed split ordering, bounds, topology, tensor count, tensor family, and exact tensor-type verification with zero errors.
The artifact loaded resident across four H100 NVL GPUs and completed 32 deterministic short generations plus eight longer no-think quality checks.
Every candidate output was non-empty with valid token IDs. Fatal/content checks passed for Korean, English, Japanese, code, arithmetic, exact JSON, and constrained-list prompts; no NaN or malformed structured output was observed.
A development ds4 CUDA runtime mapped the complete artifact on one H100 and passed full-weight, recurrent-state snapshot/restore, replay, and cold invalidation regressions.
A native sm_121a ds4 build serves the complete artifact on one DGX Spark GB10 through the OpenAI-compatible server at -c 196608 with three persistent banks. See DGX Spark for the measured point.

H100 timings are development and artifact-sanity evidence only. Do not present them as DGX Spark performance. 1,048,576-token serving on Spark is not claimed.

DGX Spark

One NVIDIA DGX Spark GB10 (128 GB unified memory, driver 610.43.02, CUDA 13.3, sm_121a). Runtime Baekpica/ds4@b2e52b9 on the dfm line. Artifact: this MXQ-v1 11-shard split. A long-lived VMM weight owner (--backend vmm --scope base --reserve-gb 16, 453 derived aligned artifacts) plus a restartable ds4-server worker:

DS4_CUDA_WEIGHT_IPC_MANIFEST="$RUN/weights.manifest" \
DS4_CUDA_WEIGHT_IPC_SCOPE=base \
DS4_SERVER_COALESCE_MAX=3 \
DS4_SERVER_COALESCE_MAX_TOKENS=4096 \
DS4_CONT_PREFILL_CHUNK=4096 \
DS4_METAL_PREFILL_CHUNK=4096 \
./ds4-server -m Solar-Open2-250B-MXQ-v1-00001-of-00011.gguf \
  --cuda -c 196608 -n 1024 -t 6 \
  --host 0.0.0.0 --port 8002 --model-id solar-open2-250b \
  --no-spec --no-update-check --mem-floor-gb 8

OpenAI Chat Completions, thinking disabled, exact-cold (cached_tokens=0), 128 decode tokens, median of three. Loaded SM clocks 2,411–2,561 MHz. banks_total=3 still admitted.

Depth	Prompt tokens	Prefill	Decode p50	Decode API
8K	8,222	1,050.7 tok/s	19.05 tok/s	18.9 tok/s
64K	66,761	804.5 tok/s	13.07 tok/s	14.1 tok/s

On the same host and artifact, before the dfm default-path series that ends at b2e52b9, 8K decode was 17.5 tok/s and 64K average prefill was 710 tok/s. The series kept the production path as: skip width-1 inner CUDA graph capture; walk FATTN KV in 32-key then GQA-pair 64-key tiles; keep the KDA 64 KiB state tile in shared memory; tile grouped GQA decode KV in 32 keys with packed K-FP8/V-FP4 dequant.

test-solar-kv on this binary: 512-token GQA2 vs one-head rel_rms=0; split vs direct rel_rms=8.45e-7. Incremental T(64K)−T(60K) last-4K is not a published figure. Native 1,048,576-token metadata is not a measured Spark pass.

Partial prefix reuse

Runtime Baekpica/ds4@042bcea adds a bounded, shared Solar KDA checkpoint pool to the continuous lane. The 32 slots are demand-mapped, exact forks share references, and long prefills retain roughly 24 periodic checkpoints across the configured context in addition to request boundaries. A divergent prompt restores the nearest safe checkpoint and replays only the gap.

One controlled A/B run used the same GB10, artifact, four-bank worker, -c 65536, 4,096-token prefill chunks, and greedy no-think Chat requests. The control set DS4_SERVER_FORK_PARTIAL=0, which also disables checkpoint reservation. The treatment used the default.

Request	Prompt	Treatment cached	Control TTFT	Treatment TTFT	Speedup
Source	12,123	0	10,654.0 ms	10,710.7 ms	0.995×
Branch at ~6K	6,079	4,096	5,323.7 ms	1,868.8 ms	2.85×
Branch at ~10K	10,148	8,192	8,920.2 ms	1,929.8 ms	4.62×

Both branch responses were byte-identical between control and treatment. Treatment reported two partial-fork admits, 12,288 cached tokens, zero failed requests, and zero admission rejects. Source checkpoint capture added 56.7 ms (0.53%) in this single run. After the three requests, device-live memory was 102.04 GiB and system-available memory was 14.59 GiB with an 8 GiB floor.

This is a bounded worker-local cache, not an unbounded radix tree. Token history and GQA prefix rows remain anchored to a retained bank, and the KDA checkpoint pool is not serialized into disk-KV payloads.

Provenance

Source: upstage/Solar-Open2-250B@9190fbe63a2ad8e17fc766ccceb36de7c66f004b
Official implementation oracle: upstageAI/transformers@ef5c37485091057070b36dd0620798f74988eb01
llama.cpp conversion base: ggml-org/llama.cpp@6ea215d171fd31df943bf1ac8227129f2b963160
Solar conversion/runtime patch SHA-256: 7c267850de7a08af66a9bd64e9d4a3b33e085a4d2888d94a4c3d919f87283e44
Reproduction repository: Baekpica/solar-open2-mixed-ds4

Current upstream runtimes may not yet recognize the solar-open2 GGUF architecture. Use a compatible Solar Open 2 llama.cpp port or the linked ds4 development branch; compatibility claims should be tied to an exact runtime revision.

License and attribution

The source model and this derivative artifact are distributed under the included Upstage Solar License. The model name begins with Solar, and this card prominently states “Built with Solar” as required by that license.