Roleplay Xing4.0 29B — Hardware Requirements & GPU Compatibility
ChatRoleplay
Roleplay Xing4.0 29B is a 31.2B-parameter open language model from hunter-P. It supports a context window of up to 262,144 tokens. At BF16 it needs about 63.90 GB of VRAM — see which GPUs and Macs can run it below.
Roleplay Xing4.0 29B runs on a 96 GB+ Mac or a workstation GPU
Best local pick → Mac Studio (M3 Ultra, 96GB) · BF16 · 72.1 GB · ~36 tok/s
Macs from 96 GB (BF16 · ~36 tok/s)
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Roleplay Xing4.0 29B
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 hunter-P/roleplay-Xing4.0-29B --max-model-len 16384 --tensor-parallel-size 8vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX PRO 6000 (96 GB) (23 GB headroom) · BF16
- Generation speed
- ~85 tok/s
- generation speed
- Cost per 1M output tokens
- $4.11
- per 1M output tokens
How Much VRAM Does Roleplay Xing4.0 29B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 63.9 GB | 81.5 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on H100 SXM 80 GB |
Selected BF16
Brain floating point 1672.1GBat 16K context
- Weights
- 62.4 GB
- KV cache
- 9.4 GB
- Overhead
- 0.3 GB
Server-class: ~72.1 GB at 16K context · one H100 SXM 80 GB
Or .
Which Hardware Can Run Roleplay Xing4.0 29B?
BF16 · 63.9 GBRoleplay Xing4.0 29B (BF16) requires 63.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 84+ GB is recommended. Using the full 262K context window can add up to 149.2 GB, bringing total usage to 213.1 GB. No consumer GPU has enough memory. 31 devices with unified memory can run Roleplay Xing4.0 29B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio (M3 Ultra, 96GB).
64–80 GB
tight · up to 2K ctx
5 GPUs · 1 device family
H100 SXM~137Simulate output on H100 SXMA100 80GB SXM~94Simulate output on A100 80GB SXMH100 PCIe~94Simulate output on H100 PCIeOrin~12Simulate output on NVIDIA Jetson AGX Orin 64GB96 GB
fits · 23.9 GB free · up to 32K ctx
3 GPUs · 2 Mac classes
RTX PRO 6000 Blackwell Max-Q Workstation Edition~85Simulate output on RTX PRO 6000 Blackwell Max-Q Workstation EditionRTX PRO 6000 Blackwell Workstation Edition~85Simulate output on RTX PRO 6000 Blackwell Workstation EditionRTX PRO 6000 Blackwell Server Edition~77Simulate output on RTX PRO 6000 Blackwell Server EditionM3 Ultra*96 GB~36Simulate output on Mac Studio (M3 Ultra, 96GB)M3 Max*96 GB~16Simulate output on MacBook Pro 14" M3 Max (96 GB)128–144 GB
fits · 55.9 GB free · up to 64K ctx
4 GPUs · 2 Mac classes · 4 device families
GH200 Grace Hopper Superchip~175Simulate output on GH200 Grace Hopper SuperchipH200 NVL~173Simulate output on H200 NVLH200 SXM~173Simulate output on H200 SXMM2 Ultra*128 GB~36Simulate output on Mac Pro M2 Ultra (128 GB)M5 Max128 GB~29Simulate output on Mac Studio M5 Max (128 GB)GB10~15Simulate output on NVIDIA DGX SparkJetson T5000 (Thor)~15Simulate output on NVIDIA Jetson AGX Thor Developer Kit
By VRAM tier · typical GPUs and Macs at BF16
Consumer GPUs (up to 32 GB) and Macs up to 64 GB: too small for this model (needs ≥ 72.1 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Hy Memory 30B A3BTencent | — | 19.1 GB | ~184 | same size |
| Granite Switch 4.1 30BIBM | — | 22.7 GB | ~35 | 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 | — | 21.7 GB | ~32 | same size |
Specifications
- Publisher
- hunter-P
- Parameters
- 31.2B
- Active parameters
- 5.5B per token
- Architecture
- Xing4_0ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2026-09-18
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Roleplay Xing4.0 29B need?
Roleplay Xing4.0 29B requires 63.9 GB of VRAM at BF16. Full 262K context adds up to 149.2 GB (213.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 31.2B × 16 bits ÷ 8 = 62.4 GB
KV Cache + Overhead ≈ 1.5 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 ≈ 150.7 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Roleplay Xing4.0 29B?
No — Roleplay Xing4.0 29B requires at least 63.9 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run Roleplay Xing4.0 29B on a Mac?
Yes — Mac Studio (M3 Ultra, 96GB) and 20 other Macs can run Roleplay Xing4.0 29B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 63.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run Roleplay Xing4.0 29B locally?
Yes — Roleplay Xing4.0 29B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Roleplay Xing4.0 29B?
At BF16, Roleplay Xing4.0 29B can reach ~97 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 11.2 GB active ÷ (8000 × 0.65) = 2.15 ms, plus 40 layers × 0.055 ms = 2.20 ms, so 1000 ÷ 4.35 ms = ~230 tok/s
Estimated speed at BF16 (63.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Roleplay Xing4.0 29B?
At BF16, the download is about 62.43 GB.
Which GPUs can run Roleplay Xing4.0 29B?
No single consumer GPU has enough VRAM to run Roleplay Xing4.0 29B at BF16 (63.9 GB). Multi-GPU or professional hardware is required.
Which devices can run Roleplay Xing4.0 29B?
31 devices with unified memory can run Roleplay Xing4.0 29B at BF16 (63.9 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (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.