Instella 3B — Hardware Requirements & GPU Compatibility
Chat
Instella 3B is a 3.1B-parameter open language model from amd. It supports a context window of up to 4,096 tokens. At BF16 it needs about 7.28 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 2K)Best on 24 GB (BF16 · ~90 tok/s · 4K)Macs from 16 GB (BF16 · ~19 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Instella 3B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve amd/Instella-3B --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 (4 GB headroom) · BF16
- Generation speed
- ~32 tok/s
- generation speed
- Cost per 1M output tokens
- $0.60
- per 1M output tokens
How Much VRAM Does Instella 3B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 7.3 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 4K context · ~90 tok/s |
Selected BF16
Brain floating point 168.0GBat 4K context
- Weights
- 6.2 GB
- KV cache
- 1.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 16.0 GB free · ~90 tok/s
≥50 tok/s needs ≥559 GB/s · RTX 5090 ~160, RTX 3090 Ti ~90
Which Hardware Can Run Instella 3B?
BF16 · 7.3 GBInstella 3B (BF16) requires 7.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 10+ GB is recommended. Using the full 4K context window can add up to 0.8 GB, bringing total usage to 8.0 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080. 151 devices with unified memory can run Instella 3B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA Jetson Orin Nano 8GB (Super).
12 GB
12 GB tier →fits · 4.0 GB free · up to 4K ctx
10 GPUs
RTX 3080 Ti~82Simulate output on RTX 3080 TiRTX 5070~60Simulate output on RTX 5070RTX 4070~45Simulate output on RTX 407020 GB
fits · 12.0 GB free · up to 4K ctx
1 GPU
RX 7900 XT~66Simulate output on RX 7900 XT32–40 GB
fits · 24.0 GB free · up to 4K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~160Simulate output on RTX 5090M5 Max36 GB~44Simulate output on Mac Studio M5 Max (36 GB)M532 GB~15Simulate output on MacBook Air 13" M5 (32 GB)Orin~18Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~12Simulate 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 |
|---|---|---|---|---|
| SmolLM3 3BHugging Face | — | 3.4 GB | ~285 | same size |
| Llama 3.2 3B InstructMeta | — | 4.1 GB | ~309 | same size |
| AI21 Jamba Reasoning 3BAI21 Labs | — | 2.3 GB | ~291 | same size |
| Qwen2.5 3B InstructAlibaba | — | 2.8 GB | ~294 | same size |
| MiniMax M3 EAGLE3Inferact | — | 2.7 GB | ~284 | same size |
| Tiny Aya BaseCohere | — | 9.4 GB | ~89 | same size |
Specifications
- Publisher
- amd
- Parameters
- 3.1B
- Architecture
- InstellaForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 50,304
- Release Date
- 2025-03-05
- License
- Other
Frequently Asked Questions
How much VRAM does Instella 3B need?
Instella 3B requires 7.3 GB of VRAM at BF16. Full 4K context adds up to 0.8 GB (8.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3.1B × 16 bits ÷ 8 = 6.2 GB
KV Cache + Overhead ≈ 1.1 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 ≈ 1.8 GB (at full 4K context)
VRAM usage by quantization
Can I run Instella 3B on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Instella 3B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 7.3 GB of usable unified memory (RAM minus macOS overhead).
Can I run Instella 3B locally?
Yes — Instella 3B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Instella 3B?
At BF16, Instella 3B can reach ~659 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~90 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 ÷ 7.28 × 0.65 = ~714 tok/s
Estimated speed at BF16 (7.3 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Instella 3B?
At BF16, the download is about 6.23 GB.
Which GPUs can run Instella 3B?
52 consumer GPUs can run Instella 3B at BF16. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 38 GPUs have plenty of headroom for comfortable inference.
Which devices can run Instella 3B?
151 devices with unified memory can run Instella 3B at BF16 (7.3 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.