LLMs ·

Solar Open 2 250B

Parameters
250B (15.0B active)
Architecture
Mixture of experts
Max context
1,024K tokens
License
solar-open
Released
2026-07

How to run it

Original weights · Hugging Face

Full-precision files from Upstage, for fine-tuning, vLLM, Transformers.

huggingface.co/upstage/Solar-Open2-250B (opens in a new tab)

No sign-in needed.

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

Apps that run Solar Open 2 250B

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, AMD Radeon

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good:

App Type Opens it as Systems Engine Start
vLLM Server Original weights WSLWindowsLinux vLLM 
vllm serve upstage/Solar-Open2-250B
SGLang Server Original weights WSLWindowsLinux SGLang 
python3 -m sglang.launch_server --model-path upstage/Solar-Open2-250B
Docker Model Runner CLI + API Original weights macOSWindowsLinux llama.cpp, vLLM 
docker model run hf.co/upstage/Solar-Open2-250B
Text Generation WebUI Desktop app Original weights macOSWindowsLinux llama.cpp, Transformers, ExLlamaV3 Get Text Generation WebUI

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 100 GB 102 GB 107 GB All files (opens in a new tab)
Q3_K_M Low 123 GB 125 GB 130 GB All files (opens in a new tab)
Q4_K_M Good 153 GB 155 GB 160 GB All files (opens in a new tab)
Q5_K_M High 178 GB 180 GB 185 GB All files (opens in a new tab)
Q6_K High 205 GB 207 GB 212 GB All files (opens in a new tab)
Q8_0 Very high 265 GB 268 GB 272 GB All files (opens in a new tab)
F16 Full 501 GB 503 GB 508 GB Original weights (opens in a new tab)

Best hardware for Solar Open 2 250B

Quality Hardware Quant Memory Speed Runs
85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Apple Mac Studio (2025) (M4 Max or M3 Ultra)Apple M3 Ultra (256 GB) Q4_K_M 170 GB / 192 GB 48.3 tok/s Runs welltight fit
87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Apple Mac Studio (2025) (M4 Max or M3 Ultra)Apple M3 Ultra (512 GB) Q5_K_M 211 GB / 384 GB 40.9 tok/s Runs great
75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Apple Mac Studio (2023) (M2 Max or M2 Ultra)Apple M2 Ultra (192 GB) Q3_K_M 136 GB / 144 GB 59.0 tok/s Runs welltight fit
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA DGX SparkNVIDIA GB10 (128 GB) Q2_K 112 GB / 115 GB 32.9 tok/s Runs welltight fit
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Workstation EditionNVIDIA RTX PRO 6000 Blackwell Q2_K 107 GB / 96.0 GB 52.0 tok/s Runs welloffloads to RAM
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. ASUS ProArt P16 (H7607BA)NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) Q2_K 111 GB / 102 GB 30.4 tok/s Runs wellover GPU memory limit
89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI350XAMD Instinct MI350X Q6_K 222 GB / 288 GB 162 tok/s Runs great
89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Apple Mac Studio (M5 Max or M5 Ultra)Apple M5 Ultra (512 GB) Q6_K 238 GB / 384 GB 48.4 tok/s Runs great
87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI325XAMD Instinct MI325X Q5_K_M 193 GB / 256 GB 157 tok/s Runs great
87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Dell Pro Max with GB300NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip Q5_K_M 193 GB / 252 GB 179 tok/s Runs great

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?