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 Q5_K_M it needs about 1.34 GB of VRAM — see which GPUs and Macs can run it below.
161.6K downloads
712 likesSpecifications
- Publisher
- sapientinc
- Parameters
- 1.2B
- Architecture
- HrmTextForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 65,536
- Release Date
- 2026-05-21
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does HRM Text 1B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q5_K_M | 5.70 | 1.3 GB | 1.6 GB | 0.84 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 1.5 GB | 1.7 GB | 0.98 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 1.7 GB | 1.9 GB | 1.18 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run HRM Text 1B?
Q5_K_M · 1.3 GBHRM Text 1B (Q5_K_M) requires 1.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ GB is recommended. Using the full 4K context window can add up to 0.2 GB, bringing total usage to 1.6 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run HRM Text 1B?
Q5_K_M · 1.3 GB33 devices with unified memory can run HRM Text 1B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Derivatives (3)
Frequently Asked Questions
- How much VRAM does HRM Text 1B need?
HRM Text 1B requires 1.3 GB of VRAM at Q5_K_M, or 1.7 GB at Q8_0.
VRAM = Weights + KV Cache + Overhead
Weights = 1.2B × 5.7 bits ÷ 8 = 0.8 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 0.8 GB (at full 4K context)
VRAM usage by quantization
Q5_K_M1.3 GBQ5_K_M + full context1.6 GB- What's the best quantization for HRM Text 1B?
For HRM Text 1B, Q6_K (1.5 GB) offers the best balance of quality and VRAM usage. Q8_0 (1.7 GB) provides better quality if you have the VRAM. The smallest option is Q5_K_M at 1.3 GB.
VRAM requirement by quantization
Q5_K_M1.3 GBQ6_K ★1.5 GBQ8_01.7 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run HRM Text 1B on a Mac?
HRM Text 1B requires at least 1.3 GB at Q5_K_M, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run HRM Text 1B locally?
Yes — HRM Text 1B can run locally on consumer hardware. At Q5_K_M quantization it needs 1.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is HRM Text 1B?
At Q5_K_M, HRM Text 1B can reach ~2175 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~489 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 1.3 × 0.55 = ~2175 tok/s
Estimated speed at Q5_K_M (1.3 GB)
~2175 tok/s~489 tok/s~1626 tok/s~1345 tok/sReal-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 Q5_K_M, the download is about 0.84 GB. The full-precision Q8_0 version is 1.18 GB.
- Which GPUs can run HRM Text 1B?
35 consumer GPUs can run HRM Text 1B at Q5_K_M (1.3 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run HRM Text 1B?
33 devices with unified memory can run HRM Text 1B at Q5_K_M (1.3 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.