Darwin 60B DUO — Hardware Requirements & GPU Compatibility
ChatReasoning
Darwin 60B DUO is a 60B-parameter open language model from FINAL-Bench. At BF16 it needs about 132.00 GB of VRAM — see which GPUs and Macs can run it below.
Darwin 60B DUO runs on a 192 GB+ Mac or a datacenter GPU
Best local pick → Mac Pro M2 Ultra (192 GB) · BF16 · 136.5 GB · ~4 tok/s
Macs from 192 GB (BF16 · ~4 tok/s)
Gemma Terms
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Darwin 60B DUO
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve FINAL-Bench/Darwin-60B-DUO --max-model-len 16384 --tensor-parallel-size 8vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on B200 (192 GB) (55 GB headroom) · BF16
- Generation speed
- ~39 tok/s
- generation speed
- Cost per 1M output tokens
- $42.16
- per 1M output tokens
How Much VRAM Does Darwin 60B DUO Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 132 GB | 141.7 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on H200 NVL 141 GB |
Selected BF16
Brain floating point 16136.5GBat 16K context
- Weights
- 131.1 GB
- KV cache
- 5.2 GB
- Overhead
- 0.3 GB
Server-class: ~136.5 GB at 16K context · one H200 NVL 141 GB
Which Hardware Can Run Darwin 60B DUO?
BF16 · 132 GBDarwin 60B DUO (BF16) requires 132 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 172+ GB is recommended. No consumer GPU has enough memory. 4 devices with unified memory can run Darwin 60B DUO, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Pro M2 Ultra (192 GB).
192+ GB
fits · 55.5 GB free · up to 32K ctx
6 GPUs · 1 Mac class · 2 device families
B200~39Simulate output on B200B300~39Simulate output on B300Instinct MI350X~36Simulate output on Instinct MI350XM3 Ultra256–512 GB~4Simulate output on Mac Studio (M3 Ultra, 256GB)8x H100 SXM5~132Simulate output on NVIDIA DGX H1008x A100 SXM4~80Simulate output on NVIDIA DGX A100 640GB
By VRAM tier · typical GPUs and Macs at BF16
Consumer GPUs (up to 32 GB) and Macs up to 128 GB: too small for this model (needs ≥ 136.5 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Similar models
2| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen2 57B A14B InstructAlibaba | — | 35.7 GB | —needs > 24 GB | same size |
| Mixtral 34Bx2 MoE 60Bcloudyu | — | 40.8 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- FINAL-Bench
- Parameters
- 60B
- Architecture
- DarwinDuoOrchestrator
- Release Date
- 2026-05-27
- License
- Gemma Terms
Frequently Asked Questions
How much VRAM does Darwin 60B DUO need?
Darwin 60B DUO requires 132 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 60B × 16 bits ÷ 8 = 120 GB
KV Cache + Overhead ≈ 12 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.
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Darwin 60B DUO?
No — Darwin 60B DUO requires at least 132 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run Darwin 60B DUO on a Mac?
Yes — Mac Pro M2 Ultra (192 GB) and 3 other Macs can run Darwin 60B DUO. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 132 GB of usable unified memory (RAM minus macOS overhead).
Can I run Darwin 60B DUO locally?
Yes — Darwin 60B DUO can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Darwin 60B DUO?
At BF16, Darwin 60B DUO can reach ~36 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 132.0 × 0.65 = ~39 tok/s
Estimated speed at BF16 (132 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Darwin 60B DUO?
At BF16, the download is about 120.00 GB.
Which GPUs can run Darwin 60B DUO?
No single consumer GPU has enough VRAM to run Darwin 60B DUO at BF16 (132 GB). Multi-GPU or professional hardware is required.
Which devices can run Darwin 60B DUO?
4 devices with unified memory can run Darwin 60B DUO at BF16 (132 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.