TLive Omni 4B — Hardware Requirements & GPU Compatibility
ChatVisionFunctions
TLive Omni 4B is a 5.8B-parameter open language model from TaoLiveAIGC. It supports a context window of up to 262,144 tokens. At BF16 it needs about 12.11 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs from 16 GB (BF16 · 32K)Best on 24 GB (BF16 · ~54 tok/s · 128K)Macs from 16 GB (BF16 · ~12 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run TLive Omni 4B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve TaoLiveAIGC/TLive-Omni-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 5060 Ti 16GB (2 GB headroom) · BF16
- Generation speed
- ~24 tok/s
- generation speed
- Cost per 1M output tokens
- $1.90
- per 1M output tokens
How Much VRAM Does TLive Omni 4B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 12.1 GB | 14.6 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 128K context · ~54 tok/s |
Selected BF16
Brain floating point 1613.3GBat 16K context
- Weights
- 11.6 GB
- KV cache
- 1.3 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 10.7 GB free · ~54 tok/s
≥50 tok/s needs ≥931 GB/s · RTX 5090 ~96, RTX 3090 Ti ~54
Which Hardware Can Run TLive Omni 4B?
BF16 · 12.1 GBTLive Omni 4B (BF16) requires 12.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 16+ GB is recommended. Using the full 262K context window can add up to 21.3 GB, bringing total usage to 33.4 GB. 26 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080. 150 devices with unified memory can run TLive Omni 4B, 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 · 2.7 GB free · up to 32K ctx
18 GPUs · 2 Mac classes · 2 device families
RTX 5080~52Simulate output on RTX 5080RTX 5070 Ti~48Simulate output on RTX 5070 TiRTX 4080 SUPER~40Simulate output on RTX 4080 SUPERM516 GB~9Simulate output on MacBook Air 13" M5 (16 GB)M3 Pro*18 GB~9Simulate output on MacBook Pro 14" M3 Pro (18 GB)iPad~7Simulate output on iPad Pro M4 13" (16 GB)Orin NX~6Simulate output on NVIDIA Jetson Orin NX 16GB20 GB
fits · 6.7 GB free · up to 64K ctx
1 GPU
RX 7900 XT~40Simulate output on RX 7900 XT32–40 GB
fits · 18.7 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~96Simulate output on RTX 5090M5 Max36 GB~27Simulate output on Mac Studio M5 Max (36 GB)M532 GB~9Simulate output on MacBook Air 13" M5 (32 GB)Orin~11Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~7Simulate 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 3n E2B ITGoogle | — | 5.9 GB | ~183 | same size |
| Qwen2.5 Omni 3BAlibaba | — | 6 GB | ~180 | same size |
| Yi 6B Chat01.AI | — | 4.2 GB | ~161 | same size |
| Chatglm3 6BZ.ai | — | 5.2 GB | ~159 | same size |
| T5gemma 2B 2B Ul2Google | — | 6 GB | ~178 | same size |
| Yi 1.5 6B Chat01.AI | — | 4.2 GB | ~161 | same size |
Specifications
- Publisher
- TaoLiveAIGC
- Parameters
- 5.8B
- Architecture
- TLiveOmniForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-08-14
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does TLive Omni 4B need?
TLive Omni 4B requires 12.1 GB of VRAM at BF16. Full 262K context adds up to 21.3 GB (33.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 5.8B × 16 bits ÷ 8 = 11.6 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 ≈ 21.8 GB (at full 262K context)
VRAM usage by quantization
Can I run TLive Omni 4B on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run TLive Omni 4B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 12.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run TLive Omni 4B locally?
Yes — TLive Omni 4B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is TLive Omni 4B?
At BF16, TLive Omni 4B can reach ~396 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~54 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 ÷ 12.11 × 0.65 = ~429 tok/s
Estimated speed at BF16 (12.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of TLive Omni 4B?
At BF16, the download is about 11.65 GB.
Which GPUs can run TLive Omni 4B?
26 consumer GPUs can run TLive Omni 4B at BF16. Top options include AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, AMD Radeon RX 6800. 8 GPUs have plenty of headroom for comfortable inference.
Which devices can run TLive Omni 4B?
150 devices with unified memory can run TLive Omni 4B at BF16 (12.1 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.