Solar Open 100B hardware requirements
What is Solar Open 100B?
Solar Open 100B is Upstage's flagship model, trained from scratch and released in January 2026. It is a mixture-of-experts model with 102B total and 12B active parameters, aimed at reasoning, instruction following and agentic tasks in Korean and English, with up to 128k tokens of context. Its Upstage Solar License builds on Apache 2.0 and allows commercial use, but derivative model names must begin with Solar.
About the model
- Parameters
- 102.65B total · 12B active (MoE)
- Attention
- Full attention
- Max context
- 131,072 tokens
- Released
- 2025-12-10
- Model card
- Solar Open 100B on Hugging Face
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| Q2_K | 37.69 GB | Heavy loss | Community GGUF · mradermacher |
| IQ4_XS | 55.53 GB | Good balance | Community GGUF · mradermacher |
| Q4_K_Mbaseline | 62.26 GB | Good balance | Community GGUF · mradermacher |
| Q8_0 | 109.15 GB | Near-lossless | Community GGUF · mradermacher |
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k |
|---|---|---|---|---|---|---|
| Q2_K | 38.8 | 39.6 | 41.3 | 44.7 | 51.4 | 64.9 |
| IQ4_XS | 56.4 | 57.3 | 59.0 | 62.3 | 69.1 | 82.6 |
| Q4_K_M | 63.1 | 64.0 | 65.7 | 69.0 | 75.8 | 89.3 |
| Q8_0 | 109.6 | 110.5 | 112.2 | 115.5 | 122.3 | 135.8 |
Which GPUs can run Solar Open 100B?
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 |
|---|---|---|---|---|---|---|---|---|
| NVIDIA RTX PRO 6000 Blackwell | Runs great | est. 102.3 tok/s81.9–122.8calibrated estimate ±20% | Q4_K_M | 64.6 / 96.0 GB | Full GPU | up to 128k | — | — |
| NVIDIA RTX PRO 6000 Blackwell Max-Q | Runs great | est. 102.3 tok/s81.9–122.8calibrated estimate ±20% | Q4_K_M | 64.6 / 96.0 GB | Full GPU | up to 128k | — | — |
| Apple M5 Ultra · 96 GB | Runs great | est. 56.5 tok/s45.2–67.8calibrated estimate ±20% | Q4_K_M | 64.4 / 67.2 GB | Unified memory | up to 16k | — | — |
| Apple M5 Max (40-core GPU) · 128 GB | Runs great | est. 45.3 tok/s36.2–54.3calibrated estimate ±20% | Q4_K_M | 64.4 / 89.6 GB | Unified memory | up to 32k | — | — |
| Apple M3 Ultra · 96 GB | Runs great | est. 42.0 tok/s33.6–50.4calibrated estimate ±20% | Q4_K_M | 64.4 / 67.2 GB | Unified memory | up to 16k | — | — |
| Apple M2 Ultra · 128 GB | Runs great | est. 41.3 tok/s33.0–49.5calibrated estimate ±20% | Q4_K_M | 64.4 / 89.6 GB | Unified memory | up to 16k | — | — |
| Apple M4 Max (40-core GPU) · 128 GB | Runs great | est. 41.0 tok/s32.8–49.3calibrated estimate ±20% | Q4_K_M | 64.4 / 89.6 GB | Unified memory | up to 16k | — | — |
| NVIDIA DGX Spark · 128 GB | Runs well | est. 22.8 tok/s18.3–27.4calibrated estimate ±20% | Q4_K_M | 64.4 / 116.9 GB | Unified memory | up to 32k |
| $3,999 launch MSRP (128 GB) |
| Ryzen AI Max+ 395 (Strix Halo) · 128 GB | Runs well | est. 21.6 tok/s17.3–26.0calibrated estimate ±20% | Q4_K_M | 64.4 / 89.6 GB | Unified memory | up to 32k | — | $1,999 launch MSRP (128 GB) |
| DDR5-6000 dual-channel CPU · 96 GB | Runs slowly | est. 4.6 tok/s3.7–5.6calibrated estimate ±20% | Q4_K_M | 63.9 GB RAM | CPU only | up to 32k | — | — |
| DDR5-5600 dual-channel CPU · 96 GB | Runs slowly | est. 4.3 tok/s3.5–5.2calibrated estimate ±20% | Q4_K_M | 63.9 GB RAM | CPU only | up to 16k | — | — |
| GeForce RTX 3090 Ti | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 28.9 tok/s20.2–37.5theoretical estimate ±30% | Q2_K | 22.7 / 24.0 GB + 17.8 GB RAM | MoE experts in RAM | up to 32k |
| $1,999 launch MSRP |
| GeForce RTX 4090 | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 28.9 tok/s20.2–37.5theoretical estimate ±30% | Q2_K | 22.7 / 24.0 GB + 17.8 GB RAM | MoE experts in RAM | up to 32k |
| $2,755 street (as of 2026-08-09) |
| GeForce RTX 3090 | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 28.4 tok/s19.9–36.9theoretical estimate ±30% | Q2_K | 22.7 / 24.0 GB + 17.8 GB RAM | MoE experts in RAM | up to 32k |
| $1,050 street (as of 2026-08-09) |
| GeForce RTX 5090 Laptop | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 28.1 tok/s19.7–36.6theoretical estimate ±30% | Q2_K | 22.7 / 24.0 GB + 17.8 GB RAM | MoE experts in RAM | up to 32k |
| — |
| Radeon RX 7900 XTX | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 26.7 tok/s18.7–34.8theoretical estimate ±30% | Q2_K | 22.7 / 24.0 GB + 17.8 GB RAM | MoE experts in RAM | up to 32k |
| $999 launch MSRP |
| Radeon RX 7900 XT | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 23.0 tok/s16.1–29.9theoretical estimate ±30% | Q2_K | 19.1 / 20.0 GB + 21.4 GB RAM | MoE experts in RAM | up to 32k |
| $899 launch MSRP |
| GeForce RTX 5080 | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 22.0 tok/s15.4–28.6theoretical estimate ±30% | Q2_K | 14.7 / 16.0 GB + 25.8 GB RAM | MoE experts in RAM | up to 16k |
| $1,256 street (as of 2026-08-09) |
| GeForce RTX 5090 | Won't runTry IQ4_XS: Runs slowly | est. 21.9 tok/s15.3–28.4theoretical estimate ±30% | IQ4_XS | 30.8 / 32.0 GB + 27.5 GB RAM | MoE experts in RAM | up to 8k |
| $4,200 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 21.8 tok/s15.2–28.3theoretical estimate ±30% | Q2_K | 14.7 / 16.0 GB + 25.8 GB RAM | MoE experts in RAM | up to 16k |
| $949 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 21.8 tok/s15.2–28.3theoretical estimate ±30% | Q2_K | 14.7 / 16.0 GB + 25.8 GB RAM | MoE experts in RAM | up to 16k |
| — |
| GeForce RTX 4080 Super | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 21.0 tok/s14.7–27.3theoretical estimate ±30% | Q2_K | 14.7 / 16.0 GB + 25.8 GB RAM | MoE experts in RAM | up to 16k |
| $999 launch MSRP |
| GeForce RTX 4080 | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 20.9 tok/s14.6–27.2theoretical estimate ±30% | Q2_K | 14.7 / 16.0 GB + 25.8 GB RAM | MoE experts in RAM | up to 16k |
| $1,199 launch MSRP |
| GeForce RTX 4070 Ti Super | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 20.7 tok/s14.5–26.9theoretical estimate ±30% | Q2_K | 14.7 / 16.0 GB + 25.8 GB RAM | MoE experts in RAM | up to 16k |
| $799 launch MSRP |
| GeForce RTX 4090 Laptop | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 20.0 tok/s14.0–26.0theoretical estimate ±30% | Q2_K | 14.7 / 16.0 GB + 25.8 GB RAM | MoE experts in RAM | up to 16k |
| — |
| Radeon RX 9070 | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 19.6 tok/s13.7–25.5theoretical estimate ±30% | Q2_K | 14.7 / 16.0 GB + 25.8 GB RAM | MoE experts in RAM | up to 16k |
| $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 19.6 tok/s13.7–25.5theoretical estimate ±30% | Q2_K | 14.7 / 16.0 GB + 25.8 GB RAM | MoE experts in RAM | up to 16k |
| $689 street (as of 2026-08-09) |
| Radeon RX 7800 XT | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 19.5 tok/s13.6–25.3theoretical estimate ±30% | Q2_K | 14.7 / 16.0 GB + 25.8 GB RAM | MoE experts in RAM | up to 16k |
| $499 launch MSRP |
| GeForce RTX 5060 Ti 16GB | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 18.7 tok/s13.1–24.4theoretical estimate ±30% | Q2_K | 14.7 / 16.0 GB + 25.8 GB RAM | MoE experts in RAM | up to 16k |
| $569 street (as of 2026-08-09) |
| Radeon RX 9060 XT 16GB | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 16.5 tok/s11.6–21.5theoretical estimate ±30% | Q2_K | 14.7 / 16.0 GB + 25.8 GB RAM | MoE experts in RAM | up to 16k |
| $449 street (as of 2026-08-09) |
| Apple M5 Pro · 64 GB | Won't runTry IQ4_XS: Runs slowly | est. 16.3 tok/s11.4–21.2theoretical estimate ±30% | IQ4_XS | 57.1 GB RAM | CPU only | up to 16k |
| — |
| GeForce RTX 4060 Ti 16GB | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 16.2 tok/s11.4–21.1theoretical estimate ±30% | Q2_K | 14.7 / 16.0 GB + 25.8 GB RAM | MoE experts in RAM | up to 16k |
| $499 launch MSRP |
| Apple M4 Pro · 64 GB | Won't runTry IQ4_XS: Runs slowly | est. 14.5 tok/s10.1–18.8theoretical estimate ±30% | IQ4_XS | 57.1 GB RAM | CPU only | up to 16k |
| — |
| DDR4-3200 dual-channel CPU · 64 GB | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 3.7 tok/s2.9–4.4calibrated estimate ±20% | Q2_K | 39.3 GB RAM | CPU only | up to 8k | — | — |
| Apple M4 · 32 GB | Won't run | — | Q4_K_M | needs 64.4 GB | — | — |
| — |
| Apple M4 Max (32-core GPU) · 36 GB | Won't run | — | Q4_K_M | needs 64.4 GB | — | — |
| — |
| Apple M5 · 32 GB | Won't run | — | Q4_K_M | needs 64.4 GB | — | — |
| — |
| Apple M5 Max (32-core GPU) · 36 GB | Won't run | — | Q4_K_M | needs 64.4 GB | — | — |
| — |
| Apple M6 · 32 GB | Won't run | — | Q4_K_M | needs 64.4 GB | — | — |
| — |
| Intel Arc B580 | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $290 street (as of 2026-08-09) |
| GeForce GTX 1080 Ti | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $699 launch MSRP |
| GeForce RTX 2080 Ti | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $999 launch MSRP |
| GeForce RTX 3050 8GB | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $249 launch MSRP |
| GeForce RTX 3060 12GB | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $250 street (as of 2026-08-09) |
| GeForce RTX 3070 | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $499 launch MSRP |
| GeForce RTX 3080 10GB | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $699 launch MSRP |
| GeForce RTX 3080 12GB | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $799 launch MSRP |
| GeForce RTX 4060 | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $299 launch MSRP |
| GeForce RTX 4060 Laptop | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| — |
| GeForce RTX 4060 Ti 8GB | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $399 launch MSRP |
| GeForce RTX 4070 | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $599 launch MSRP |
| GeForce RTX 4070 Laptop | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| — |
| GeForce RTX 4070 Super | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $599 launch MSRP |
| GeForce RTX 4080 Laptop | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| — |
| GeForce RTX 5060 | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $429 street (as of 2026-08-09) |
| GeForce RTX 5070 | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Won't run | — | Q4_K_M | needs 64.0 GB | — | — |
| — |
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 Q4_K_M. The table above lists Macs, unified-memory PCs and CPU setups.
Measured results for Solar Open 100B
No public measurements for this model yet.
Frequently asked questions
How much VRAM does Solar Open 100B need?
At Q4_K_M the file is 62.26 GB; with 8k context a graphics card needs about 64.0 GB (weights 61.79 GB, KV cache 1.6 GB, compute buffer 0.6 GB). The smallest tracked file (Q2_K (heavy quality loss)) needs about 39.6 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 100B well?
No GPU with a current street price reaches Runs great or Runs well at Q4_K_M. Counting hardware with only a launch price too, the best option is NVIDIA DGX Spark · 128 GB: Runs well.
Can Solar Open 100B run on an 8 GB, 16 GB or 24 GB GPU?
At Q4_K_M 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.