Huihui MoE 23B A4B Abliterated — Hardware Requirements & GPU Compatibility
Chat
Huihui MoE 23B A4B Abliterated is a 23.2B-parameter open language model from huihui-ai. It supports a context window of up to 40,960 tokens. At Q4_K_M it needs about 14.43 GB of VRAM — see which GPUs and Macs can run it below.
239 downloads
4 likesSpecifications
- Publisher
- huihui-ai
- Parameters
- 23.2B
- Architecture
- Qwen3MoeForCausalLM
- Context Length
- 40,960 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2025-06-21
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Huihui MoE 23B A4B Abliterated Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 10.4 GB | 13.9 GB | 9.88 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 11.8 GB | 15.4 GB | 11.33 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 14.4 GB | 18.0 GB | 13.94 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 17.1 GB | 20.6 GB | 16.56 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 19.7 GB | 23.3 GB | 19.17 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 23.7 GB | 27.3 GB | 23.24 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 47.0 GB | 50.5 GB | 46.48 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Huihui MoE 23B A4B Abliterated?
Q4_K_M · 14.4 GBHuihui MoE 23B A4B Abliterated (Q4_K_M) requires 14.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 19+ GB is recommended. Using the full 41K context window can add up to 3.6 GB, bringing total usage to 18.0 GB. 26 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Huihui MoE 23B A4B Abliterated?
Q4_K_M · 14.4 GB47 devices with unified memory can run Huihui MoE 23B A4B Abliterated, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 (16 GB).
Runs great
— Plenty of headroomFrequently Asked Questions
- How much VRAM does Huihui MoE 23B A4B Abliterated need?
Huihui MoE 23B A4B Abliterated requires 14.4 GB of VRAM at Q4_K_M, or 47.0 GB at BF16. Full 41K context adds up to 3.6 GB (18.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 23.2B × 4.8 bits ÷ 8 = 13.9 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 4.1 GB (at full 41K context)
VRAM usage by quantization
Q4_K_M14.4 GBQ4_K_M + full context18.0 GB- Can NVIDIA GeForce RTX 4090 run Huihui MoE 23B A4B Abliterated?
Yes, at Q8_0 (23.7 GB) or lower. Higher quantizations like BF16 (47.0 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Huihui MoE 23B A4B Abliterated?
For Huihui MoE 23B A4B Abliterated, Q4_K_M (14.4 GB) offers the best balance of quality and VRAM usage. Q5_K_M (17.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 10.4 GB.
VRAM requirement by quantization
Q2_K10.4 GBQ4_K_M ★14.4 GBQ5_K_M17.1 GBQ6_K19.7 GBQ8_023.7 GBBF1647.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Huihui MoE 23B A4B Abliterated on a Mac?
Huihui MoE 23B A4B Abliterated requires at least 10.4 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Huihui MoE 23B A4B Abliterated locally?
Yes — Huihui MoE 23B A4B Abliterated can run locally on consumer hardware. At Q4_K_M quantization it needs 14.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Huihui MoE 23B A4B Abliterated?
At Q4_K_M, Huihui MoE 23B A4B Abliterated can reach ~305 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~45 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 ÷ 14.4 × 0.65 = ~360 tok/s
Estimated speed at Q4_K_M (14.4 GB)
~360 tok/s~45 tok/s~360 tok/s~305 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Huihui MoE 23B A4B Abliterated?
At Q4_K_M, the download is about 13.94 GB. The full-precision BF16 version is 46.48 GB. The smallest option (Q2_K) is 9.88 GB.
- Which GPUs can run Huihui MoE 23B A4B Abliterated?
26 consumer GPUs can run Huihui MoE 23B A4B Abliterated at Q4_K_M (14.4 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3090 Ti, AMD Radeon RX 6800. 7 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Huihui MoE 23B A4B Abliterated?
49 devices with unified memory can run Huihui MoE 23B A4B Abliterated at Q4_K_M (14.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.