DarkIdol Qwen3.8 27B V1.1 Voice — Hardware Requirements & GPU Compatibility
ChatRoleplay
DarkIdol Qwen3.8 27B V1.1 Voice is a 27B-parameter open language model from Wiself in the Qwen 3.8 family. At BF16 it needs about 59.40 GB of VRAM — see which GPUs and Macs can run it below.
DarkIdol Qwen3.8 27B V1.1 Voice runs on a 64 GB+ Mac or a workstation GPU
Best local pick → Mac Pro M2 Ultra (64 GB) · BF16 · 63 GB · ~9 tok/s
Macs from 64 GB (BF16 · ~9 tok/s)
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run DarkIdol Qwen3.8 27B V1.1 Voice
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 Wiself/DarkIdol-Qwen3.8-27B-v1.1-Voice --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on H100 (80 GB) (17 GB headroom) · BF16
- Generation speed
- ~37 tok/s
- generation speed
- Cost per 1M output tokens
- $20.36
- per 1M output tokens
How Much VRAM Does DarkIdol Qwen3.8 27B V1.1 Voice Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 59.4 GB | 67.1 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 63 GB |
Selected BF16
Brain floating point 1663.0GBat 16K context
- Weights
- 58.6 GB
- KV cache
- 4.1 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 39.0 GB more
Or .
Which Hardware Can Run DarkIdol Qwen3.8 27B V1.1 Voice?
BF16 · 59.4 GBDarkIdol Qwen3.8 27B V1.1 Voice (BF16) requires 59.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 78+ GB is recommended. No consumer GPU has enough memory. 52 devices with unified memory can run DarkIdol Qwen3.8 27B V1.1 Voice, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Pro M2 Ultra (64 GB).
64–80 GB
fits · 1.0 GB free · up to 16K ctx
3 Mac classes · 1 device family
M2 Ultra*64 GB~9Simulate output on Mac Pro M2 Ultra (64 GB)M5 Max64 GB~7Simulate output on Mac Studio M5 Max (64 GB)Orin~2Simulate output on NVIDIA Jetson AGX Orin 64GB
By VRAM tier · typical GPUs and Macs at BF16
Alternatives to DarkIdol Qwen3.8 27B V1.1 Voice
Qwen 3.8 family · 12 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.6 27BAlibaba | 111.2 | 17.9 GB | ~38 | same size |
| Qwen3.5 27BAlibaba | 103.8 | 17.9 GB | ~38 | same size |
| Gemma 3 27B ITGoogle | 79.4 | 21.7 GB | ~36 | same size |
| Gemma 2 27B ITGoogle | 72.7 | 19.5 GB | ~37 | same size |
| Gemma 4 26B A4BGoogle | — | 16.5 GB | ~171 | same size |
| Ariarhymes-ai | — | 20.2 GB | ~168 | same size |
Specifications
- Publisher
- Wiself
- Family
- Qwen 3.8
- Parameters
- 27B
- Release Date
- 2026-09-13
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does DarkIdol Qwen3.8 27B V1.1 Voice need?
DarkIdol Qwen3.8 27B V1.1 Voice requires 59.4 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 27B × 16 bits ÷ 8 = 54 GB
KV Cache + Overhead ≈ 5.4 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.
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run DarkIdol Qwen3.8 27B V1.1 Voice?
No — DarkIdol Qwen3.8 27B V1.1 Voice requires at least 59.4 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run DarkIdol Qwen3.8 27B V1.1 Voice on a Mac?
Yes — Mac Pro M2 Ultra (64 GB) and 41 other Macs can run DarkIdol Qwen3.8 27B V1.1 Voice. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 59.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run DarkIdol Qwen3.8 27B V1.1 Voice locally?
Yes — DarkIdol Qwen3.8 27B V1.1 Voice can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is DarkIdol Qwen3.8 27B V1.1 Voice?
At BF16, DarkIdol Qwen3.8 27B V1.1 Voice can reach ~81 tok/s on AMD Instinct MI350X. 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 ÷ 59.4 × 0.65 = ~88 tok/s
Estimated speed at BF16 (59.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of DarkIdol Qwen3.8 27B V1.1 Voice?
At BF16, the download is about 54.00 GB.
Which GPUs can run DarkIdol Qwen3.8 27B V1.1 Voice?
No single consumer GPU has enough VRAM to run DarkIdol Qwen3.8 27B V1.1 Voice at BF16 (59.4 GB). Multi-GPU or professional hardware is required.
Which devices can run DarkIdol Qwen3.8 27B V1.1 Voice?
52 devices with unified memory can run DarkIdol Qwen3.8 27B V1.1 Voice at BF16 (59.4 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.