Baidu, China · Released June 19, 2026
Unlimited-OCR has 3.34B parameters (0.7B active per token). In BF16 its weights alone take 6.21 GiB; quantized to 4-bit, about 1.85 GiB. Each 32K-token request adds 0.01 GiB of KV cache. Cheapest way to run it today: 1 × RTX A4000 (16 GB) at $0.082 per hour. It reads text and images.
Size your own setup in the calculator →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 |
|---|---|---|---|
| BF16 / FP16 | 6.21 | 6.22 | 6.22 |
| FP8 / INT8 | 3.42 | 3.42 | 3.42 |
| 4-bit (GGUF Q4_K_M) | 1.85 | 1.86 | 1.86 |
Exact size of each quantization in sahilchachra/Unlimited-OCR-GGUF (opens in a new tab), and the smallest GPU that runs it with llama.cpp, Ollama or LM Studio and an 8K-token context.
| Quantization | File size | Smallest GPU |
|---|---|---|
| BF16 | 5.47 GiB | RTX 4060 (8 GB) |
| Q8_0 | 2.91 GiB | RTX 4060 (8 GB) |
| Q6_K | 2.43 GiB | RTX 4060 (8 GB) |
| Q5_K_M | 2.07 GiB | RTX 4060 (8 GB) |
| Q4_K_M | 1.82 GiB | RTX 4060 (8 GB) |
| IQ4_XS | 1.53 GiB | RTX 4060 (8 GB) |
| Q3_K_M | 1.45 GiB | RTX 4060 (8 GB) |
| IQ2_M | 1.15 GiB | RTX 4060 (8 GB) |
| Quantization | File size | Smallest GPU |
|---|---|---|
| Q5_K_S | 1.95 GiB | RTX 4060 (8 GB) |
| Q4_K_S | 1.68 GiB | RTX 4060 (8 GB) |
| IQ4_NL | 1.59 GiB | RTX 4060 (8 GB) |
| IQ3_M | 1.35 GiB | RTX 4060 (8 GB) |
| IQ3_XXS | 1.24 GiB | RTX 4060 (8 GB) |
Read every day from Hugging Face. Split files are added together; vision projectors are left out.
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 | 8-bit | 4-bit |
|---|---|---|---|
| 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 |
| Ryzen AI Max+ 395 128 GB 96 GB usable | 1 | 1 | 1 |
| DGX Spark (GB10) 128 GB | 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 |
8-bit: FP8 with vLLM (INT8 on GPUs without FP8), Q8_0 with llama.cpp. 4-bit: AWQ / GPTQ with vLLM, Q4_K_M with llama.cpp, both counted at the Q4_K_M size.
For each GPU: the fewest cards that fit Unlimited-OCR with one 8K-token request, the most faithful weight format at that count, and the cheapest on-demand price (2026-10-16).
| Setup | Per hour | Weights | Provider | Per month | Rent |
|---|---|---|---|---|---|
| 1 × RTX A4000 16 GB | $0.082 | BF16 | Vast.ai | $59.86 | Rent 1 × RTX A4000 on Vast.ai (opens in a new tab) → |
| 1 × GeForce RTX 3090 24 GB | $0.122 | BF16 | Vast.ai | $89.06 | Rent 1 × GeForce RTX 3090 on Vast.ai (opens in a new tab) → |
| 1 × RTX A5000 24 GB | $0.201 | BF16 | Vast.ai | $146.73 | Rent 1 × RTX A5000 on Vast.ai (opens in a new tab) → |
| 1 × GeForce RTX 5080 16 GB | $0.201 | BF16 | Vast.ai | $146.73 | Rent 1 × GeForce RTX 5080 on Vast.ai (opens in a new tab) → |
| 1 × RTX 2000 Ada 16 GB | $0.240 | BF16 | RunPod | $175.20 | Rent 1 × RTX 2000 Ada on RunPod (opens in a new tab) → |
| 1 × RTX A4500 20 GB | $0.250 | BF16 | RunPod | $182.50 | Rent 1 × RTX A4500 on RunPod (opens in a new tab) → |
| 1 × RTX PRO 4000 Blackwell 24 GB | $0.257 | BF16 | Vast.ai | $187.61 | Rent 1 × RTX PRO 4000 Blackwell on Vast.ai (opens in a new tab) → |
| 1 × NVIDIA L4 24 GB | $0.268 | BF16 | Vast.ai | $195.64 | Rent 1 × NVIDIA L4 on Vast.ai (opens in a new tab) → |
On-demand prices from AWS, Google Cloud, Azure, RunPod, Vast.ai, Oracle Cloud, OVHcloud, Scaleway, Verda, Akash and UpCloud, 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.
AWS, Google Cloud and UpCloud prices: Spare Cores (opens in a new tab), CC BY-SA 4.0 (opens in a new tab), shared under the same license.
Architecture: 12 layers · 12 sliding-window layers (128 tokens, 10 KV × 128). Its KV cache is 256.0× smaller than if every layer used full attention, because most layers only keep a short window of recent tokens. Only 0.7B parameters are active per token, but all 3B must sit in memory: VRAM depends on the total, speed on the active part.
| Context per request | BF16 cache | FP8 cache |
|---|---|---|
| 8K tokens | 0.01 GiB | 0.00 GiB |
| 32K tokens | 0.01 GiB | 0.00 GiB |
In BF16 the weights alone take 6.21 GiB (6.7 GB). In FP8 that is 3.42 GiB, and about 1.85 GiB with 4-bit quantization (Q4_K_M). Each request then adds KV cache: 0.01 GiB at 8K tokens and 0.01 GiB at 32K (BF16 cache).
Yes. In BF16 it fits on one RTX 4090 with an 8K-token context (6.22 GiB including the cache, with llama.cpp).
Yes. In BF16 (6.22 GiB with an 8K-token context) it fits on one RTX 5090, with llama.cpp.
Yes. In 4-bit (Q4_K_M with llama.cpp) it needs a Mac with 8 GB of unified memory or more, of which macOS gives the GPU about 5 GB, for one request with an 8K-token context. The same Mac also holds it in 8-bit (Q8_0).
Yes. In BF16 (6.22 GiB with an 8K-token context) it fits on a DGX Spark (128 GB) and on a Ryzen AI Max+ 395 with 128 GB, whose GPU gets up to 96 GB, with llama.cpp and one request.
On 2026-10-16, the cheapest on-demand setup is 1 × RTX A4000 (16 GB) with BF16 weights on Vast.ai, at $0.082 per hour (about $59.86 per month). Next: 1 × GeForce RTX 3090 (24 GB) with BF16 weights on Vast.ai, at $0.122 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.
Yes. Unlimited-OCR reads text and images. Images add tokens to the context, so they also add KV cache.
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/unlimited-ocr.json.
Baidu, China · Released June 19, 2026[](https://studiotvai.com/vram-requirements/unlimited-ocr)Same family (sliding-window attention): 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 · Humanizer · Mellum2.1 12B-A2.5B · Spark-X2.5 4B · Ministral 8B · Gemma 4 E4B · Gemma 4 E2B
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 · Youtu-Parsing-Omni · Agnes-3.0-Flash · Mistral 7B v0.3 · Mistral Small 3.1 24B · Mistral Nemo · Ministral 8B · DeepSeek V3 · DeepSeek R1 Qwen3 8B · DeepSeek R1 Distill Qwen 32B · DeepSeek V3.1 · DeepSeek R1 Distill Qwen 14B · DeepSeek R1 Distill Qwen 7B · DeepSeek R1 Distill Llama 8B · Qwen3 4B · Qwen3 8B · Qwen2.5 7B · Qwen3 14B · Qwen2.5 3B · Qwen3.6 27B · Qwen3.5 27B · Qwen2.5-Coder 7B · Qwen2.5 32B · Qwen2.5-Coder 14B · Qwen3.5 35B-A3B · Qwen3 30B-A3B · Qwen2.5 14B · Qwen2.5-Coder 32B · Kimi K2.7 Code · Kimi K2.5 · Kimi K2 · GLM-5.2 · GLM-5.1 · GLM-5 · MiniMax M2.5 · MiniMax M2 · MiMo-V2.5 · Ornith-1.0 397B · Qwen2.5-Coder 3B · Qwen3 235B-A22B · Qwen3.5 397B-A17B · Gemma 4 E4B · Gemma 4 E2B · Nemotron 3 Nano 4B · Nemotron 3.5 Lightning 30B-A3B · MiniCPM-V-4.7 35B-A3B · LFM2.5 24B-A2B · GLM-4.7 · Qwen3-VL 8B · Qwen2.5-VL 7B · Qwen3-VL 4B · Qwen2.5-VL 3B · Qwen2.5-VL 32B · Qwen2-VL 7B · GLM-4.5-Air · GLM-4.5 · phi-4 · Phi-3.5-mini · Phi-4-mini · Phi-3-mini-128k · Ling-3.1-flash · Step-5-Preview
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.