HRM Text 1B — Hardware Requirements & GPU Compatibility
Chat
HRM Text 1B is a 1.2B-parameter open language model from sapientinc. It supports a context window of up to 4,096 tokens. At BF16 it needs about 2.87 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 4K)Best on 24 GB (BF16 · ~228 tok/s · 4K)Macs from 8 GB (BF16 · ~25 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run HRM Text 1B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve sapientinc/HRM-Text-1B --max-model-len 4096vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (8 GB headroom) · BF16
- Generation speed
- ~82 tok/s
- generation speed
- Cost per 1M output tokens
- $0.28
- per 1M output tokens
How Much VRAM Does HRM Text 1B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.9 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 4K context · ~228 tok/s |
Selected BF16
Brain floating point 163.1GBat 4K context
- Weights
- 2.4 GB
- KV cache
- 0.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 20.9 GB free · ~228 tok/s
≥50 tok/s needs ≥221 GB/s · RTX 5090 ~406, RTX 3090 Ti ~228
Which Hardware Can Run HRM Text 1B?
BF16 · 2.9 GBHRM Text 1B (BF16) requires 2.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 4K context window can add up to 0.2 GB, bringing total usage to 3.1 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run HRM Text 1B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 4.9 GB free · up to 4K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~172Simulate output on RTX 3080RTX 2080 Ti~140Simulate output on RTX 2080 TiRTX 3070 Ti~138Simulate output on RTX 3070 TiM3*8 GB~25Simulate output on iMac 24" M3 (8 GB)Orin Nano~23Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~17Simulate output on iPhone 1720 GB
fits · 16.9 GB free · up to 4K ctx
1 GPU
RX 7900 XT~167Simulate output on RX 7900 XT32–40 GB
fits · 28.9 GB free · up to 4K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~406Simulate output on RTX 5090M5 Max36 GB~112Simulate output on Mac Studio M5 Max (36 GB)M532 GB~38Simulate output on MacBook Air 13" M5 (32 GB)Orin~46Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~31Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Llama 3.2 1B InstructMeta | — | 2.3 GB | ~799 | same size |
| TinyLlama 1.1B Chat v1.0TinyLlama | — | 1 GB | ~649 | same size |
| LFM2.5 1.2B ThinkingLiquid AI | — | 1.2 GB | ~612 | same size |
| LFM2 1.2BLiquid AI | — | 1.2 GB | ~612 | same size |
| T5gemma L L Ul2 ITGoogle | — | 4.3 GB | ~240 | same size |
| OLMo 1B HFAllen AI | — | 1.3 GB | ~516 | same size |
Fine-tunes & variants(2)
Specifications
- Publisher
- sapientinc
- Parameters
- 1.2B
- Architecture
- HrmTextForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 65,536
- Release Date
- 2026-05-17
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does HRM Text 1B need?
HRM Text 1B requires 2.9 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 1.2B × 16 bits ÷ 8 = 2.4 GB
KV Cache + Overhead ≈ 0.5 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 ≈ 0.7 GB (at full 4K context)
VRAM usage by quantization
Can I run HRM Text 1B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run HRM Text 1B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 2.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run HRM Text 1B locally?
Yes — HRM Text 1B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is HRM Text 1B?
At BF16, HRM Text 1B can reach ~1673 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~228 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 ÷ 2.87 × 0.65 = ~1812 tok/s
Estimated speed at BF16 (2.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of HRM Text 1B?
At BF16, the download is about 2.37 GB.
Which GPUs can run HRM Text 1B?
52 consumer GPUs can run HRM Text 1B 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 HRM Text 1B?
163 devices with unified memory can run HRM Text 1B at BF16 (2.9 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.