Darwin 180B RSI R3 — Hardware Requirements & GPU Compatibility
VisionReasoningFunctionsDarwin 180B RSI R3 is a 180.0B-parameter open language model from FINAL-Bench. It supports a context window of up to 262,144 tokens. At BF16 it needs about 360.38 GB of VRAM — see which GPUs and Macs can run it below.
Darwin 180B RSI R3 runs on a 512 GB+ Mac or a multi-GPU server
Best local pick → Mac Studio M5 Ultra (512 GB) · BF16 · 361 GB · ~7 tok/s
Macs from 512 GB (BF16 · ~7 tok/s)
Other
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Darwin 180B RSI R3
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve FINAL-Bench/Darwin-180B-RSI-R3 --max-model-len 16384 --tensor-parallel-size 8Size the nodes from the table above
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Rent 6× H100 SXM · BF16
- Estimated hourly price
- ~$16.14/hr
- est., whole server
- GPUs
- 6 GPUs
- 480 GB of VRAM
$5+ bonus for new users
How Much VRAM Does Darwin 180B RSI R3 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 360.4 GB | 361.6 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on 6× H100 SXM 80 GB |
Selected BF16
Brain floating point 16361.0GBat 16K context
- Weights
- 360.0 GB
- KV cache
- 0.7 GB
- Overhead
- 0.3 GB
Server-class: ~361 GB at 16K context · about 6× H100 SXM 80 GB
Which Hardware Can Run Darwin 180B RSI R3?
BF16 · 360.4 GBDarwin 180B RSI R3 (BF16) requires 360.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 469+ GB is recommended. Using the full 262K context window can add up to 10.7 GB, bringing total usage to 371.0 GB. No consumer GPU has enough memory. 2 devices with unified memory can run Darwin 180B RSI R3, including Mac Studio M5 Ultra (512 GB).
Needs server-class hardware
Darwin 180B RSI R3 runs on a 512 GB+ Mac or a multi-GPU server · BF16 needs ~361 GB
| Hardware | Quant | Memory | Speed | Context | Hardware page | |
|---|---|---|---|---|---|---|
| Mac 512 GB · Mac Studio M5 Ultra (512 GB) | BF16 | 361 GB | ~7 tok/s | 256K ctx | Mac Studio M5 Ultra → | BF16 · 361 GB · ~7 tok/s · 256K ctx |
| 6× H100 SXM 80 GB · 480 GB | BF16 | 361 GB | — | 256K ctx | H100 SXM → | BF16 · 361 GB · 256K ctx |
| 3× H200 SXM 141 GB · 423 GB | BF16 | 361 GB | — | 256K ctx | H200 SXM → | BF16 · 361 GB · 256K ctx |
| 3× B200 192 GB · 576 GB | BF16 | 361 GB | — | 256K ctx | B200 → | BF16 · 361 GB · 256K ctx |
Also: AMD Instinct MI355X Platform (8x MI355X) · Mac Studio (M3 Ultra, 512GB) · Mac Studio M5 Ultra (512 GB) · NVIDIA DGX A100 640GB · NVIDIA DGX B200 · NVIDIA DGX B300 · NVIDIA DGX H100 · NVIDIA DGX H200 · NVIDIA GB200 NVL72 · NVIDIA GB300 NVL72
By VRAM tier · typical GPUs and Macs at BF16
Consumer GPUs (up to 32 GB) and Macs up to 256 GB: too small for this model (needs ≥ 361 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Similar models
1| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.8 Flash NextAlibaba | — | 109 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- FINAL-Bench
- Parameters
- 180.0B
- Active parameters
- 61.6B per token
- Architecture
- Qwen4ExpForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-10-01
- License
- Other
Frequently Asked Questions
How much VRAM does Darwin 180B RSI R3 need?
Darwin 180B RSI R3 requires 360.4 GB of VRAM at BF16. Full 262K context adds up to 10.7 GB (371.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 180.0B × 16 bits ÷ 8 = 360 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 11 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Darwin 180B RSI R3?
No — Darwin 180B RSI R3 requires at least 360.4 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run Darwin 180B RSI R3 on a Mac?
Yes — Mac Studio M5 Ultra (512 GB) and 1 other Mac can run Darwin 180B RSI R3. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 360.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run Darwin 180B RSI R3 locally?
Yes — Darwin 180B RSI R3 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of Darwin 180B RSI R3?
At BF16, the download is about 360.00 GB.
Which GPUs can run Darwin 180B RSI R3?
No single consumer GPU has enough VRAM to run Darwin 180B RSI R3 at BF16 (360.4 GB). Multi-GPU or professional hardware is required.
Which devices can run Darwin 180B RSI R3?
2 devices with unified memory can run Darwin 180B RSI R3 at BF16 (360.4 GB), including Mac Studio (M3 Ultra, 512GB), Mac Studio M5 Ultra (512 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.