TildeOpen 30B — Hardware Requirements & GPU Compatibility
Chat
TildeOpen 30B is a 30.7B-parameter open language model from TildeAI. It supports a context window of up to 65,536 tokens. At Q4_K_M it needs about 19.21 GB of VRAM — see which GPUs and Macs can run it below.
Decent on a 24 GB GPU
Runs on 24 GB (Q4_K_M · ~34 tok/s · 16K)Macs from 24 GB (Q4_K_M · ~11 tok/s)
CC BY 4.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run TildeOpen 30B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve TildeAI/TildeOpen-30b --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 PRO 4500 (32 GB) (9 GB headroom) · Q4_K_M
- Generation speed
- ~30 tok/s
- generation speed
- Cost per 1M output tokens
- $3.12
- per 1M output tokens
How Much VRAM Does TildeOpen 30B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 13.8 GB | 21.4 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~47 tok/s | |
| 15.8 GB | 23.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~42 tok/s | |
| 19.2 GB | 26.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 16K context · ~34 tok/s | |
| 22.7 GB | 30.2 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 4K context · ~29 tok/s | |
| 26.1 GB | 33.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 29.6 GB | |
| 31.5 GB | 39 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 35 GB | |
| 62.2 GB | 69.7 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 65.7 GB |
Selected Q4_K_M
4-bit medium quantization22.7GBat 16K context
- Weights
- 18.4 GB
- KV cache
- 4.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 1.3 GB free · ~34 tok/s
≥50 tok/s needs ≥1.48 TB/s · RTX 5090 ~61
Which Hardware Can Run TildeOpen 30B?
Q4_K_M · 19.2 GBTildeOpen 30B (Q4_K_M) requires 19.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 25+ GB is recommended. Using the full 66K context window can add up to 15.6 GB, bringing total usage to 34.8 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run TildeOpen 30B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
tight · up to 4K ctx
1 GPU
RX 7900 XT~25Simulate output on RX 7900 XT32–40 GB
fits · 9.3 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~61Simulate output on RTX 5090M5 Max36 GB~17Simulate output on Mac Studio M5 Max (36 GB)M532 GB~6Simulate output on MacBook Air 13" M5 (32 GB)Orin~7Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~5Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Hy Memory 30B A3BTencent | — | 19.1 GB | ~184 | same size |
| Muse Glimmer 30BMeta | — | 19.6 GB | ~36 | same size |
| NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA | — | 19.3 GB | ~197 | same size |
| Hy MT2 30B A3BTencent | — | 19.1 GB | ~170 | same size |
| Gemma 4 31BGoogle | — | 22.6 GB | ~31 | same size |
| GLM 4.7 FlashZ.ai | — | 19.9 GB | ~142 | same size |
Specifications
- Publisher
- TildeAI
- Parameters
- 30.7B
- Architecture
- LlamaForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2025-08-19
- License
- CC BY 4.0
Frequently Asked Questions
How much VRAM does TildeOpen 30B need?
TildeOpen 30B requires 19.2 GB of VRAM at Q4_K_M, or 62.2 GB at BF16. Full 66K context adds up to 15.6 GB (34.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 30.7B × 4.8 bits ÷ 8 = 18.4 GB
KV Cache + Overhead ≈ 0.8 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 ≈ 16.4 GB (at full 66K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run TildeOpen 30B?
Yes, at Q5_K_M (22.7 GB) or lower. Higher quantizations like Q6_K (26.1 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for TildeOpen 30B?
For TildeOpen 30B, Q4_K_M (19.2 GB) offers the best balance of quality and VRAM usage. Q5_K_M (22.7 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 13.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run TildeOpen 30B on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run TildeOpen 30B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 19.2 GB of usable unified memory (RAM minus macOS overhead).
Can I run TildeOpen 30B locally?
Yes — TildeOpen 30B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is TildeOpen 30B?
At Q4_K_M, TildeOpen 30B can reach ~250 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~34 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 ÷ 19.2 × 0.65 = ~271 tok/s
Estimated speed at Q4_K_M (19.2 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of TildeOpen 30B?
At Q4_K_M, the download is about 18.41 GB. The full-precision BF16 version is 61.36 GB. The smallest option (Q2_K) is 13.04 GB.
Which GPUs can run TildeOpen 30B?
8 consumer GPUs can run TildeOpen 30B at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run TildeOpen 30B?
122 devices with unified memory can run TildeOpen 30B at Q4_K_M (19.2 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.