Tencent, China · Released October 9, 2026New
Youtu-Parsing-Omni has 5.33B parameters. In BF16 its weights alone take 9.94 GiB; quantized to 4-bit, about 2.80 GiB. Each 32K-token request adds 1.41 GiB of KV cache. Cheapest way to run it today: 1 × GeForce RTX 3090 (24 GB) at $0.136 per hour.
Size your own setup in the calculator →vLLM needs the extra setup described on the model card (model card (opens in a new tab))
Weights plus the KV cache of one request (BF16 cache), in GiB. Add 1 to 3 GiB for the inference engine itself.
| Weights format | Weights only | + 8K context | + 32K context | + 128K context | + 1M context |
|---|---|---|---|---|---|
| BF16 / FP16 | 9.94 | 10.3 | 11.3 | 15.6 | 54.9 |
| FP8 / INT8 | 5.61 | 5.96 | 7.01 | 11.2 | 50.6 |
| 4-bit (GGUF Q4_K_M) | 2.80 | 3.15 | 4.20 | 8.42 | 47.8 |
Fewest GPUs that fit the weights plus one 8K-token request. Data-center GPUs use vLLM (90% of memory usable), the others llama.cpp. Several GPUs split the model with tensor or pipeline parallelism.
| GPU | BF16 / FP16 | FP8 / INT8 | 4-bit (GGUF Q4_K_M) |
|---|---|---|---|
| GeForce RTX 4090 24 GB | 1 | 1 | 1 |
| GeForce RTX 5090 32 GB | 1 | 1 | 1 |
| RTX PRO 6000 Blackwell 96 GB | 1 | 1 | 1 |
| Mac M5 Max 128 GB 96 GB usable | 1 | 1 | 1 |
| NVIDIA H100 80 GB | 1 | 1 | 1 |
| NVIDIA H200 141 GB | 1 | 1 | 1 |
| NVIDIA B200 (HGX) 180 GB | 1 | 1 | 1 |
For each GPU: the fewest cards that fit Youtu-Parsing-Omni with one 8K-token request, the most faithful weight format at that count, and the cheapest on-demand price (2026-10-10).
| Setup | Per hour | Weights | Provider | Per month | Rent |
|---|---|---|---|---|---|
| 1 × GeForce RTX 3090 24 GB | $0.136 | BF16 / FP16 | Vast.ai | $99.28 | Rent 1 × GeForce RTX 3090 on Vast.ai (opens in a new tab) → |
| 1 × GeForce RTX 5080 16 GB | $0.223 | BF16 / FP16 | Vast.ai | $162.79 | Rent 1 × GeForce RTX 5080 on Vast.ai (opens in a new tab) → |
| 1 × NVIDIA L4 24 GB | $0.268 | BF16 / FP16 | Vast.ai | $195.64 | Rent 1 × NVIDIA L4 on Vast.ai (opens in a new tab) → |
| 1 × GeForce RTX 4090 24 GB | $0.349 | BF16 / FP16 | Vast.ai | $254.77 | Rent 1 × GeForce RTX 4090 on Vast.ai (opens in a new tab) → |
| 1 × NVIDIA A100 40GB | $0.428 | BF16 / FP16 | Vast.ai | $312.44 | Rent 1 × NVIDIA A100 40GB on Vast.ai (opens in a new tab) → |
| 1 × GeForce RTX 5090 32 GB | $0.445 | BF16 / FP16 | Vast.ai | $324.85 | Rent 1 × GeForce RTX 5090 on Vast.ai (opens in a new tab) → |
| 1 × RTX 6000 Ada 48 GB | $0.494 | BF16 / FP16 | Vast.ai | $360.62 | Rent 1 × RTX 6000 Ada on Vast.ai (opens in a new tab) → |
| 1 × NVIDIA L40S 48 GB | $0.536 | BF16 / FP16 | Vast.ai | $391.28 | Rent 1 × NVIDIA L40S on Vast.ai (opens in a new tab) → |
On-demand prices from RunPod, Vast.ai, Verda and Azure, checked every hour. Serving many users needs more KV cache, so more memory: size it in the calculator. Some links are affiliate links: StudioTV may earn a commission, at no extra cost to you.
Architecture: 40 layers · MLA (512 + 64 latent) on 40. Its cache stays compact because MLA stores one compressed latent per token and layer instead of full keys and values.
| Context per request | BF16 cache | FP8 cache |
|---|---|---|
| 8K tokens | 0.35 GiB | 0.18 GiB |
| 32K tokens | 1.41 GiB | 0.70 GiB |
| 128K tokens | 5.63 GiB | 2.81 GiB |
| 1M tokens | 45.0 GiB | 22.5 GiB |
In BF16 the weights alone take 9.94 GiB (10.7 GB). In FP8 that is 5.61 GiB, and about 2.80 GiB with 4-bit quantization (Q4_K_M). Each request then adds KV cache: 0.35 GiB at 8K tokens and 1.41 GiB at 32K (BF16 cache).
Yes. In BF16 / FP16 it fits on one RTX 4090 with an 8K-token context (10.3 GiB including the cache, with llama.cpp).
On 2026-10-10, the cheapest on-demand setup is 1 × GeForce RTX 3090 (24 GB) with BF16 / FP16 weights on Vast.ai, at $0.136 per hour (about $99.28 per month). Next: 1 × GeForce RTX 5080 (16 GB) with BF16 / FP16 weights on Vast.ai, at $0.223 per hour. Sized for one 8K-token request; prices are checked every hour.
With one request and an 8K-token context: 1 in BF16, 1 in FP8 and 1 in 4-bit (vLLM, 90% of memory usable). Serving many users at once needs more memory for their KV caches: the calculator sizes that for you.
For a model card or a README: the 4-bit size and the smallest GPU it fits on, linked to this page. Data as JSON: /api/models/youtu-parsing-omni.json.
Tencent, China · Released October 9, 2026[](https://studiotvai.com/vram-requirements/youtu-parsing-omni)Same family (dense): Llama 3.1 8B · Mistral Small 3.2 24B · Qwen3 32B · Llama 3.3 70B · Llama 3.1 405B
All models: Llama 3.1 8B · Mistral Small 3.2 24B · Qwen3 32B · Llama 3.3 70B · Llama 3.1 405B · Qwen3.5 4B · Qwen3.5 9B · Qwen3.8 27B · Qwen3.6 35B-A3B · Qwen3.5 122B-A10B · Qwen3.8-Flash-Next · LFM2.5 8B-A1B · LFM2 24B-A2B · Gemma 4 12B · Gemma 4 31B · Gemma 4 26B-A4B · gpt-oss 20B · gpt-oss 120B · Llama 4 Scout 17B-16E · Llama 4 Maverick 17B-128E · Kolibri-1 · Nemotron 3 Nano 30B-A3B · Nemotron 3 Super 120B-A12B · MiniMax M2.7 · DeepSeek R1 · Kimi K2.6 · GLM-5.3 · GLM-5.3-Flash · DeepSeek V4 Flash · DeepSeek V4 Pro · DeepSeek V4.1 Flash · MiMo-V2.6 Pro · MiMo-V2.6 Flash · Kimi K3 · Mistral Large 4 · Qwen3-Coder-Next 80B-A3B · Qwen3-Coder 30B-A3B · Qwen3-Coder 480B-A35B · DeepSeek V4 Flash Vision Exp · Qwen3.8 2.4T-A95B · Ornith 1.5 397B · Ornith 1.5 35B-A3B · Ornith 1.5 9B · Atria Dawn Preview · Intern S2 397B · Clef · Clef Flash · D1 3B · Humanizer · JEV 27B VL · Mellum2.1 12B-A2.5B · LightOnOCR-3 4B · Spark-X2.5 4B · Agnes-3.0-Qwen · Agnes-3.0-Flash
Estimates, not guarantees: computed from the official config.json with the same engine as the LLM VRAM Calculator. Real usage depends on your engine version and settings.