BetterWright 4B — Hardware Requirements & GPU Compatibility
ChatFunctions
BetterWright 4B is a 4.1B-parameter open language model from ProCreations. It supports a context window of up to 1,048,576 tokens. At BF16 it needs about 8.71 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 12 GB (BF16 · 32K)Best on 24 GB (BF16 · ~75 tok/s · 128K)Macs from 16 GB (BF16 · ~16 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run BetterWright 4B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve ProCreations/BetterWright-4b --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 3060 12GB (2 GB headroom) · BF16
- Generation speed
- ~27 tok/s
- generation speed
- Cost per 1M output tokens
- $0.78
- per 1M output tokens
How Much VRAM Does BetterWright 4B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 8.7 GB | 11.5 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 128K context · ~75 tok/s |
Selected BF16
Brain floating point 1610.0GBat 16K context
- Weights
- 8.2 GB
- KV cache
- 1.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 14.0 GB free · ~75 tok/s
≥50 tok/s needs ≥669 GB/s · RTX 5090 ~134, RTX 3090 Ti ~75
Which Hardware Can Run BetterWright 4B?
BF16 · 8.7 GBBetterWright 4B (BF16) requires 8.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 12+ GB is recommended. Using the full 1049K context window can add up to 96.4 GB, bringing total usage to 105.2 GB. 40 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 BetterWright 4B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M2 Pro (16 GB).
12 GB
12 GB tier →fits · 2.0 GB free · up to 32K ctx
10 GPUs
RTX 3080 Ti~68Simulate output on RTX 3080 TiRTX 5070~50Simulate output on RTX 5070RTX 4070~38Simulate output on RTX 407020 GB
fits · 10.0 GB free · up to 64K ctx
1 GPU
RX 7900 XT~55Simulate output on RX 7900 XT32–40 GB
fits · 22.0 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~134Simulate output on RTX 5090M5 Max36 GB~37Simulate output on Mac Studio M5 Max (36 GB)M532 GB~12Simulate output on MacBook Air 13" M5 (32 GB)Orin~15Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~10Simulate 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 3 4B ITGoogle | 64.0 | 5 GB | ~231 | same size |
| Granite Vision 4.1 4BIBM | — | 4 GB | ~228 | same size |
| Qwen3 VL 4B InstructAlibaba | — | 4.5 GB | ~208 | same size |
| MiniCPM V 4OpenBMB | — | 3.1 GB | ~236 | same size |
| Phi 4 Mini ReasoningMicrosoft | — | 4.8 GB | ~228 | same size |
| Phi 3.5 Vision InstructMicrosoft | — | 9.2 GB | ~183 | same size |
Specifications
- Publisher
- ProCreations
- Parameters
- 4.1B
- Architecture
- Spark2_5ForCausalLM
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2026-09-03
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does BetterWright 4B need?
BetterWright 4B requires 8.7 GB of VRAM at BF16. Full 1049K context adds up to 96.4 GB (105.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 4.1B × 16 bits ÷ 8 = 8.2 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 ≈ 97 GB (at full 1049K context)
VRAM usage by quantization
Can I run BetterWright 4B on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run BetterWright 4B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 8.7 GB of usable unified memory (RAM minus macOS overhead).
Can I run BetterWright 4B locally?
Yes — BetterWright 4B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is BetterWright 4B?
At BF16, BetterWright 4B can reach ~551 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~75 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 ÷ 8.71 × 0.65 = ~597 tok/s
Estimated speed at BF16 (8.7 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of BetterWright 4B?
At BF16, the download is about 8.22 GB.
Which GPUs can run BetterWright 4B?
40 consumer GPUs can run BetterWright 4B 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 BetterWright 4B?
150 devices with unified memory can run BetterWright 4B at BF16 (8.7 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.