Hyenadna Medium 450k Seqlen HF — Hardware Requirements & GPU Compatibility
Chat
Hyenadna Medium 450k Seqlen HF is a 28M-parameter open language model from LongSafari. It supports a context window of up to 450,002 tokens. At BF16 it needs about 0.06 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 128K)Best on 24 GB (BF16 · ~10920 tok/s · 439K)Macs from 8 GB (BF16 · ~1195 tok/s)
BSD 3-Clause
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Hyenadna Medium 450k Seqlen HF
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 LongSafari/hyenadna-medium-450k-seqlen-hf --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (11 GB headroom) · BF16
- Generation speed
- ~9884 tok/s
- generation speed
- Cost per 1M output tokens
- $0.0034
- per 1M output tokens
How Much VRAM Does Hyenadna Medium 450k Seqlen HF Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.1 GB | 1.2 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 439K context · ~10920 tok/s |
Selected BF16
Brain floating point 160.6GBat 16K context
- Weights
- 0.1 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.4 GB free · ~10920 tok/s
≥50 tok/s needs ≥5 GB/s · RTX 5090 ~19413, RTX 3090 Ti ~10920
Which Hardware Can Run Hyenadna Medium 450k Seqlen HF?
BF16 · 0.1 GBHyenadna Medium 450k Seqlen HF (BF16) requires 0.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Hyenadna Medium 450k Seqlen HF, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 7.4 GB free · up to 128K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~8237Simulate output on RTX 3080RTX 2080 Ti~6673Simulate output on RTX 2080 TiRTX 3070 Ti~6590Simulate output on RTX 3070 TiM3*8 GB~1195Simulate output on iMac 24" M3 (8 GB)Orin Nano~1105Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~796Simulate output on iPhone 1720 GB
fits · 19.4 GB free · up to 439K ctx
1 GPU
RX 7900 XT~8000Simulate output on RX 7900 XT32–40 GB
fits · 31.4 GB free · up to 439K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~19413Simulate output on RTX 5090M5 Max36 GB~5367Simulate output on Mac Studio M5 Max (36 GB)M532 GB~1792Simulate output on MacBook Air 13" M5 (32 GB)Orin~2219Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~1463Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Specifications
- Publisher
- LongSafari
- Parameters
- 28M
- Architecture
- HyenaDNAForCausalLM
- Context Length
- 450,002 tokens
- Vocabulary Size
- 12
- Release Date
- 2023-11-03
- License
- BSD 3-Clause
Frequently Asked Questions
How much VRAM does Hyenadna Medium 450k Seqlen HF need?
Hyenadna Medium 450k Seqlen HF requires 0.1 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 28M × 16 bits ÷ 8 = 0.1 GB
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 I run Hyenadna Medium 450k Seqlen HF on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Hyenadna Medium 450k Seqlen HF. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 0.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run Hyenadna Medium 450k Seqlen HF locally?
Yes — Hyenadna Medium 450k Seqlen HF can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Hyenadna Medium 450k Seqlen HF?
At BF16, Hyenadna Medium 450k Seqlen HF can reach ~80000 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~10920 tok/s. 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 ÷ 0.06 × 0.65 = ~86667 tok/s
Estimated speed at BF16 (0.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Hyenadna Medium 450k Seqlen HF?
At BF16, the download is about 0.06 GB.
Which GPUs can run Hyenadna Medium 450k Seqlen HF?
52 consumer GPUs can run Hyenadna Medium 450k Seqlen HF at BF16. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Hyenadna Medium 450k Seqlen HF?
163 devices with unified memory can run Hyenadna Medium 450k Seqlen HF at BF16 (0.1 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.