Solar Open 2 250B hardware requirements
What is Solar Open 2 250B?
Solar Open 2 is Upstage's mixture-of-experts model from July 2026: 250B parameters, 15B active per token. It is built for agentic work such as office tasks, documents and coding, with tool calling and adjustable reasoning. It reads up to 1M tokens. Only 12 of its 48 layers keep a KV cache, so the cache is about a quarter of what it would be if every layer used full attention.
About the model
- Parameters
- 250.29B total · 15B active (MoE)
- Attention
- Hybrid attention (only some layers use full attention)
- Max context
- 1,048,576 tokens
- Released
- 2026-07-22
- Model card
- Solar Open 2 250B on Hugging Face
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| Q2_K | 95.43 GB | Heavy loss | Community GGUF · prometheusAIR |
| IQ4_XSbaseline | 136.24 GB | Good balance | Community GGUF · prometheusAIR |
| Q6_K | 205.55 GB | Near-lossless | Community GGUF · prometheusAIR |
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k | 256k |
|---|---|---|---|---|---|---|---|
| Q2_K | 95.5 | 95.7 | 96.2 | 97.2 | 99.1 | 102.9 | 110.5 |
| IQ4_XS | 136.3 | 136.5 | 137.0 | 138.0 | 139.9 | 143.7 | 151.3 |
| Q6_K | 205.6 | 205.9 | 206.3 | 207.3 | 209.2 | 213.0 | 220.7 |
Which GPUs can run Solar Open 2 250B?
How to read the verdicts
- Runs great
- Fully on the GPU at 20 tok/s or more
- Runs well
- Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
- Runs slowly
- 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
- Won't run
- Does not fit, or under 2 tok/s
Filter this list by budget, type and context in the calculator
Scroll sideways to see every column.
| Hardware | Verdict | Speed | Quant | Memory | Runs as | Context | Notes | Price |
|---|---|---|---|---|---|---|---|---|
| Apple M5 Ultra · 256 GB | Runs great | est. 50.3 tok/s40.3–60.4calibrated estimate ±20% | IQ4_XS | 137.2 / 179.2 GB | Unified memory | up to 128k | — | — |
| Apple M3 Ultra · 256 GB | Runs great | est. 37.0 tok/s29.6–44.4calibrated estimate ±20% | IQ4_XS | 137.2 / 179.2 GB | Unified memory | up to 64k | — | — |
| Apple M2 Ultra · 192 GB | Runs slowly | est. 36.3 tok/s25.4–47.2theoretical estimate ±30% | IQ4_XS | 136.6 GB RAM | CPU only | up to 256k |
| — |
| NVIDIA RTX PRO 6000 Blackwell | Won't runTry Q2_K (heavy quality loss): Runs well | est. 83.0 tok/s58.1–107.9theoretical estimate ±30% | Q2_K | 92.7 / 96.0 GB + 4.4 GB RAM | MoE experts in RAM | up to 256k |
| — |
| NVIDIA RTX PRO 6000 Blackwell Max-Q | Won't runTry Q2_K (heavy quality loss): Runs well | est. 83.0 tok/s58.1–107.9theoretical estimate ±30% | Q2_K | 92.7 / 96.0 GB + 4.4 GB RAM | MoE experts in RAM | up to 256k |
| — |
| Apple M5 Max (40-core GPU) · 128 GB | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 43.1 tok/s30.2–56.1theoretical estimate ±30% | Q2_K | 95.8 GB RAM | CPU only | up to 256k |
| — |
| Apple M4 Max (40-core GPU) · 128 GB | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 38.4 tok/s26.8–49.9theoretical estimate ±30% | Q2_K | 95.8 GB RAM | CPU only | up to 256k |
| — |
| NVIDIA DGX Spark · 128 GB | Won't runTry Q2_K (heavy quality loss): Runs well | est. 22.0 tok/s17.6–26.3calibrated estimate ±20% | Q2_K | 96.4 / 116.9 GB | Unified memory | up to 128k | — | $3,999 launch MSRP (128 GB) |
| Ryzen AI Max+ 395 (Strix Halo) · 128 GB | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 18.0 tok/s12.6–23.4theoretical estimate ±30% | Q2_K | 95.8 GB RAM | CPU only | up to 256k |
| $1,999 launch MSRP (128 GB) |
| Apple M4 · 32 GB | Won't run | — | IQ4_XS | needs 137.2 GB | — | — |
| — |
| Apple M4 Max (32-core GPU) · 36 GB | Won't run | — | IQ4_XS | needs 137.2 GB | — | — |
| — |
| Apple M4 Pro · 64 GB | Won't run | — | IQ4_XS | needs 137.2 GB | — | — |
| — |
| Apple M5 · 32 GB | Won't run | — | IQ4_XS | needs 137.2 GB | — | — |
| — |
| Apple M5 Max (32-core GPU) · 36 GB | Won't run | — | IQ4_XS | needs 137.2 GB | — | — |
| — |
| Apple M5 Pro · 64 GB | Won't run | — | IQ4_XS | needs 137.2 GB | — | — |
| — |
| Apple M6 · 32 GB | Won't run | — | IQ4_XS | needs 137.2 GB | — | — |
| — |
| Intel Arc B580 | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $290 street (as of 2026-08-09) |
| DDR4-3200 dual-channel CPU · 64 GB | Won't run | — | IQ4_XS | needs 136.6 GB | — | — |
| — |
| DDR5-5600 dual-channel CPU · 96 GB | Won't run | — | IQ4_XS | needs 136.6 GB | — | — |
| — |
| DDR5-6000 dual-channel CPU · 96 GB | Won't run | — | IQ4_XS | needs 136.6 GB | — | — |
| — |
| GeForce GTX 1080 Ti | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $699 launch MSRP |
| GeForce RTX 2080 Ti | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $999 launch MSRP |
| GeForce RTX 3050 8GB | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $249 launch MSRP |
| GeForce RTX 3060 12GB | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $250 street (as of 2026-08-09) |
| GeForce RTX 3070 | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $499 launch MSRP |
| GeForce RTX 3080 10GB | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $699 launch MSRP |
| GeForce RTX 3080 12GB | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $799 launch MSRP |
| GeForce RTX 3090 | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $1,050 street (as of 2026-08-09) |
| GeForce RTX 3090 Ti | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $1,999 launch MSRP |
| GeForce RTX 4060 | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $299 launch MSRP |
| GeForce RTX 4060 Laptop | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| — |
| GeForce RTX 4060 Ti 16GB | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $499 launch MSRP |
| GeForce RTX 4060 Ti 8GB | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $399 launch MSRP |
| GeForce RTX 4070 | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $599 launch MSRP |
| GeForce RTX 4070 Laptop | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| — |
| GeForce RTX 4070 Super | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $599 launch MSRP |
| GeForce RTX 4070 Ti Super | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $799 launch MSRP |
| GeForce RTX 4080 | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $1,199 launch MSRP |
| GeForce RTX 4080 Laptop | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| — |
| GeForce RTX 4080 Super | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $999 launch MSRP |
| GeForce RTX 4090 | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $2,755 street (as of 2026-08-09) |
| GeForce RTX 4090 Laptop | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| — |
| GeForce RTX 5060 | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 16GB | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $569 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $429 street (as of 2026-08-09) |
| GeForce RTX 5070 | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $949 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| — |
| GeForce RTX 5080 | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $1,256 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| — |
| GeForce RTX 5090 | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $4,200 street (as of 2026-08-09) |
| GeForce RTX 5090 Laptop | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| — |
| Radeon RX 7800 XT | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $499 launch MSRP |
| Radeon RX 7900 XT | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $899 launch MSRP |
| Radeon RX 7900 XTX | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $999 launch MSRP |
| Radeon RX 9060 XT 16GB | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $449 street (as of 2026-08-09) |
| Radeon RX 9070 | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Won't run | — | IQ4_XS | needs 136.5 GB | — | — |
| $689 street (as of 2026-08-09) |
Models with a thinking mode spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s). With thinking turned off, a model may do one grade better.
Cheapest GPUs that run it
No GPU with a current street price reaches Runs great or Runs well at IQ4_XS. The table above lists Macs, unified-memory PCs and CPU setups.
Measured results for Solar Open 2 250B
No public measurements for this model yet.
Frequently asked questions
How much VRAM does Solar Open 2 250B need?
At IQ4_XS the file is 136.24 GB; with 8k context a graphics card needs about 136.5 GB (weights 135.56 GB, KV cache 0.4 GB, compute buffer 0.6 GB). The smallest tracked file (Q2_K (heavy quality loss)) needs about 95.7 GB. Part of the file stays off the graphics card: llama.cpp keeps the input embedding table in system RAM. A Mac counts the whole file, so it needs a little more.
What is the cheapest GPU that runs Solar Open 2 250B well?
Nothing with a street or launch price can run it at IQ4_XS. The best tracked option, which has no listed price, is Apple M5 Ultra · 256 GB: Runs great.
Can Solar Open 2 250B run on an 8 GB, 16 GB or 24 GB GPU?
At IQ4_XS with 8k context: GeForce RTX 4060 — Won't run; GeForce RTX 5060 Ti 16GB — Won't run; GeForce RTX 3090 — Won't run.
Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.