Step 3.5 Flash Int4 Mixed AutoRound — Hardware Requirements & GPU Compatibility
Chat
280 downloads
5 likesSpecifications
- Publisher
- Intel
- Parameters
- 27.9B
- Architecture
- Step3p5ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 128,896
- Release Date
- 2026-03-14
Get Started
HuggingFace
How Much VRAM Does Step 3.5 Flash Int4 Mixed AutoRound Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| IQ4_XS | 4.30 | 16.5 GB | — | 14.99 GB | Importance-weighted 4-bit, compact |
Which GPUs Can Run Step 3.5 Flash Int4 Mixed AutoRound?
IQ4_XS · 16.5 GBStep 3.5 Flash Int4 Mixed AutoRound (IQ4_XS) requires 16.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 22+ GB is recommended. 6 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Step 3.5 Flash Int4 Mixed AutoRound?
IQ4_XS · 16.5 GB21 devices with unified memory can run Step 3.5 Flash Int4 Mixed AutoRound, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Step 3.5 Flash Int4 Mixed AutoRound need?
Step 3.5 Flash Int4 Mixed AutoRound requires 16.5 GB of VRAM at IQ4_XS.
VRAM = Weights + KV Cache + Overhead
Weights = 27.9B × 4.3 bits ÷ 8 = 15 GB
KV Cache + Overhead ≈ 1.5 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
IQ4_XS16.5 GB- Can I run Step 3.5 Flash Int4 Mixed AutoRound on a Mac?
Step 3.5 Flash Int4 Mixed AutoRound requires at least 16.5 GB at IQ4_XS, 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 Step 3.5 Flash Int4 Mixed AutoRound locally?
Yes — Step 3.5 Flash Int4 Mixed AutoRound can run locally on consumer hardware. At IQ4_XS quantization it needs 16.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Step 3.5 Flash Int4 Mixed AutoRound?
At IQ4_XS, Step 3.5 Flash Int4 Mixed AutoRound can reach ~177 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~40 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 ÷ 16.5 × 0.55 = ~177 tok/s
Estimated speed at IQ4_XS (16.5 GB)
AMD Instinct MI300X~177 tok/sNVIDIA GeForce RTX 4090~40 tok/sNVIDIA H100 SXM~132 tok/sAMD Instinct MI250X~109 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Step 3.5 Flash Int4 Mixed AutoRound?
At IQ4_XS, the download is about 14.99 GB.
- Which GPUs can run Step 3.5 Flash Int4 Mixed AutoRound?
6 consumer GPUs can run Step 3.5 Flash Int4 Mixed AutoRound at IQ4_XS (16.5 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Step 3.5 Flash Int4 Mixed AutoRound?
21 devices with unified memory can run Step 3.5 Flash Int4 Mixed AutoRound at IQ4_XS (16.5 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.