MoziAI 35B A3B MOE MTP — Hardware Requirements & GPU Compatibility
ChatVision
MoziAI 35B A3B MOE MTP is a 35B-parameter open language model from chenyumo. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 21.38 GB of VRAM — see which GPUs and Macs can run it below.
12.9K downloads
9 likesSpecifications
- Publisher
- chenyumo
- Parameters
- 35B
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-08-10
- License
- Other
Get Started
HuggingFace
How Much VRAM Does MoziAI 35B A3B MOE MTP Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 15.3 GB | 25.9 GB | 14.88 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 17.4 GB | 28.1 GB | 17.06 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 21.4 GB | 32.0 GB | 21.00 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 25.3 GB | 36.0 GB | 24.94 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 29.3 GB | 39.9 GB | 28.88 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 35.4 GB | 46.0 GB | 35.00 GB | 8-bit quantization, near-lossless |
| BF16 | 16.00 | 70.4 GB | 81.0 GB | 70.00 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 MoziAI 35B A3B MOE MTP?
Q4_K_M · 21.4 GBMoziAI 35B A3B MOE MTP (Q4_K_M) requires 21.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 28+ GB is recommended. Using the full 262K context window can add up to 10.7 GB, bringing total usage to 32.0 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090.
All compatible consumer-level GPUs are running near their VRAM limit. You may also want to consider professional GPUs (e.g., NVIDIA A100, H100) which offer significantly more VRAM. For more headroom and better throughput, consider a multi-GPU configuration with tensor parallelism (supported by tools like vLLM, llama.cpp, or text-generation-inference).
Which Devices Can Run MoziAI 35B A3B MOE MTP?
Q4_K_M · 21.4 GB41 devices with unified memory can run MoziAI 35B A3B MOE MTP, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does MoziAI 35B A3B MOE MTP need?
MoziAI 35B A3B MOE MTP requires 21.4 GB of VRAM at Q4_K_M, or 70.4 GB at BF16. Full 262K context adds up to 10.7 GB (32.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 35B × 4.8 bits ÷ 8 = 21 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 11 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M21.4 GBQ4_K_M + full context32.0 GB- Can NVIDIA GeForce RTX 4090 run MoziAI 35B A3B MOE MTP?
Yes, at Q4_K_M (21.4 GB) or lower. Higher quantizations like Q5_K_M (25.3 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for MoziAI 35B A3B MOE MTP?
For MoziAI 35B A3B MOE MTP, Q4_K_M (21.4 GB) offers the best balance of quality and VRAM usage. Q5_K_M (25.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 15.3 GB.
VRAM requirement by quantization
Q2_K15.3 GBQ4_K_M ★21.4 GBQ5_K_M25.3 GBQ6_K29.3 GBQ8_035.4 GBBF1670.4 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run MoziAI 35B A3B MOE MTP on a Mac?
MoziAI 35B A3B MOE MTP requires at least 15.3 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 MoziAI 35B A3B MOE MTP locally?
Yes — MoziAI 35B A3B MOE MTP can run locally on consumer hardware. At Q4_K_M quantization it needs 21.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is MoziAI 35B A3B MOE MTP?
At Q4_K_M, MoziAI 35B A3B MOE MTP can reach ~225 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~31 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 ÷ 21.4 × 0.65 = ~243 tok/s
Estimated speed at Q4_K_M (21.4 GB)
~243 tok/s~31 tok/s~243 tok/s~225 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of MoziAI 35B A3B MOE MTP?
At Q4_K_M, the download is about 21.00 GB. The full-precision BF16 version is 70.00 GB. The smallest option (Q2_K) is 14.88 GB.
- Which GPUs can run MoziAI 35B A3B MOE MTP?
7 consumer GPUs can run MoziAI 35B A3B MOE MTP at Q4_K_M (21.4 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
- Which devices can run MoziAI 35B A3B MOE MTP?
41 devices with unified memory can run MoziAI 35B A3B MOE MTP at Q4_K_M (21.4 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.