Bielik 4.5B V3.0 Instruct — Hardware Requirements & GPU Compatibility
Chat
Bielik 4.5B V3.0 Instruct is a 4.8B-parameter open language model from speakleash. At BF16 it needs about 10.47 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs from 12 GB (BF16 · 8K)Best on 24 GB (BF16 · ~63 tok/s · 32K)Macs from 16 GB (BF16 · ~13 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Bielik 4.5B V3.0 Instruct
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve speakleash/Bielik-4.5B-v3.0-Instruct --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 5060 Ti 16GB (3 GB headroom) · BF16
- Generation speed
- ~28 tok/s
- generation speed
- Cost per 1M output tokens
- $1.64
- per 1M output tokens
How Much VRAM Does Bielik 4.5B V3.0 Instruct Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 10.5 GB | 15.2 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~63 tok/s |
Selected BF16
Brain floating point 1612.7GBat 16K context
- Weights
- 9.9 GB
- KV cache
- 2.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 11.3 GB free · ~63 tok/s
≥50 tok/s needs ≥805 GB/s · RTX 5090 ~111, RTX 3090 Ti ~63
Which Hardware Can Run Bielik 4.5B V3.0 Instruct?
BF16 · 10.5 GBBielik 4.5B V3.0 Instruct (BF16) requires 10.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 14+ GB is recommended. 38 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti. 150 devices with unified memory can run Bielik 4.5B V3.0 Instruct, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M2 Pro (16 GB).
16–18 GB
16–18 GB tier →fits · 3.3 GB free · up to 32K ctx
18 GPUs · 2 Mac classes · 2 device families
RTX 5080~60Simulate output on RTX 5080RTX 5070 Ti~56Simulate output on RTX 5070 TiRTX 4080 SUPER~46Simulate output on RTX 4080 SUPERM516 GB~10Simulate output on MacBook Air 13" M5 (16 GB)M3 Pro*18 GB~10Simulate output on MacBook Pro 14" M3 Pro (18 GB)iPad~8Simulate output on iPad Pro M4 13" (16 GB)Orin NX~6Simulate output on NVIDIA Jetson Orin NX 16GB20 GB
fits · 7.3 GB free · up to 32K ctx
1 GPU
RX 7900 XT~46Simulate output on RX 7900 XT32–40 GB
fits · 19.3 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~111Simulate output on RTX 5090M5 Max36 GB~31Simulate output on Mac Studio M5 Max (36 GB)M532 GB~10Simulate output on MacBook Air 13" M5 (32 GB)Orin~13Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~8Simulate 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 |
|---|---|---|---|---|
| Gemma 4 E2BGoogle | — | 3.5 GB | ~191 | same size |
| Qwen3.5 4BAlibaba | — | 3.4 GB | ~201 | same size |
| Molmo2 4BAllen AI | — | 4.7 GB | ~193 | same size |
| Qwen3 VL 4B InstructAlibaba | — | 4.5 GB | ~208 | same size |
| Agents A1 4BInternScience | — | 3.4 GB | ~205 | same size |
| Qwen3.6 27B MTPLX Optimized SpeedYoussofal | — | 4 GB | ~185 | same size |
Frequently Asked Questions
How much VRAM does Bielik 4.5B V3.0 Instruct need?
Bielik 4.5B V3.0 Instruct requires 10.5 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 4.8B × 16 bits ÷ 8 = 9.5 GB
KV Cache + Overhead ≈ 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.
VRAM usage by quantization
Can I run Bielik 4.5B V3.0 Instruct on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Bielik 4.5B V3.0 Instruct. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 10.5 GB of usable unified memory (RAM minus macOS overhead).
Can I run Bielik 4.5B V3.0 Instruct locally?
Yes — Bielik 4.5B V3.0 Instruct can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Bielik 4.5B V3.0 Instruct?
At BF16, Bielik 4.5B V3.0 Instruct can reach ~459 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~63 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 ÷ 10.47 × 0.65 = ~497 tok/s
Estimated speed at BF16 (10.5 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Bielik 4.5B V3.0 Instruct?
At BF16, the download is about 9.51 GB.
Which GPUs can run Bielik 4.5B V3.0 Instruct?
38 consumer GPUs can run Bielik 4.5B V3.0 Instruct at BF16. Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 26 GPUs have plenty of headroom for comfortable inference.
Which devices can run Bielik 4.5B V3.0 Instruct?
150 devices with unified memory can run Bielik 4.5B V3.0 Instruct at BF16 (10.5 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.