Vlt5 Base Keywords — Hardware Requirements & GPU Compatibility
Chat
Vlt5 Base Keywords is a 275M-parameter open language model from Voicelab. At BF16 it needs about 0.61 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 32K)Best on 24 GB (BF16 · ~1074 tok/s · 32K)Macs from 8 GB (BF16 · ~118 tok/s)
CC BY 4.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Vlt5 Base Keywords
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve Voicelab/vlt5-base-keywords --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (10 GB headroom) · BF16
- Generation speed
- ~972 tok/s
- generation speed
- Cost per 1M output tokens
- $0.035
- per 1M output tokens
How Much VRAM Does Vlt5 Base Keywords Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.6 GB | 2.8 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~1074 tok/s |
Selected BF16
Brain floating point 161.6GBat 16K context
- Weights
- 0.2 GB
- KV cache
- 1.1 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 22.4 GB free · ~1074 tok/s
≥50 tok/s needs ≥47 GB/s · RTX 5090 ~1910, RTX 3090 Ti ~1074
Which Hardware Can Run Vlt5 Base Keywords?
BF16 · 0.6 GBVlt5 Base Keywords (BF16) requires 0.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Vlt5 Base Keywords, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 6.4 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~810Simulate output on RTX 3080RTX 2080 Ti~656Simulate output on RTX 2080 TiRTX 3070 Ti~648Simulate output on RTX 3070 TiM3*8 GB~118Simulate output on iMac 24" M3 (8 GB)Orin Nano~109Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~78Simulate output on iPhone 1720 GB
fits · 18.4 GB free · up to 32K ctx
1 GPU
RX 7900 XT~787Simulate output on RX 7900 XT32–40 GB
fits · 30.4 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~1910Simulate output on RTX 5090M5 Max36 GB~528Simulate output on Mac Studio M5 Max (36 GB)M532 GB~176Simulate output on MacBook Air 13" M5 (32 GB)Orin~218Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~144Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
2| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Gemma 3 270M ITGoogle | — | 1.2 GB | ~3640 | same size |
| Functiongemma 270M ITGoogle | — | 1.6 GB | ~1111 | same size |
Specifications
- Publisher
- Voicelab
- Parameters
- 275M
- Architecture
- T5ForConditionalGeneration
- Vocabulary Size
- 50,048
- Release Date
- 2022-09-27
- License
- CC BY 4.0
Frequently Asked Questions
How much VRAM does Vlt5 Base Keywords need?
Vlt5 Base Keywords requires 0.6 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 275M × 16 bits ÷ 8 = 0.6 GB
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 Vlt5 Base Keywords on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Vlt5 Base Keywords. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 0.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run Vlt5 Base Keywords locally?
Yes — Vlt5 Base Keywords can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Vlt5 Base Keywords?
At BF16, Vlt5 Base Keywords can reach ~7869 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1074 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 ÷ 0.61 × 0.65 = ~8525 tok/s
Estimated speed at BF16 (0.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Vlt5 Base Keywords?
At BF16, the download is about 0.55 GB.
Which GPUs can run Vlt5 Base Keywords?
52 consumer GPUs can run Vlt5 Base Keywords at BF16. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Vlt5 Base Keywords?
163 devices with unified memory can run Vlt5 Base Keywords at BF16 (0.6 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.