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.
Runs great on a 24 GB GPU
Runs from 16 GB (Q2_K · 64K)Best on 24 GB (Q4_K_M · ~174 tok/s · 256K)Macs from 24 GB (Q3_K_M · ~60 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run MoziAI 35B A3B MOE MTP
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve chenyumo/moziAI-35B-A3B-MOE-MTP --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) (10 GB headroom) · Q4_K_M
- Generation speed
- ~162 tok/s
- generation speed
- Cost per 1M output tokens
- $0.58
- per 1M output tokens
How Much VRAM Does MoziAI 35B A3B MOE MTP Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 15.3 GB | 15.5 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~212 tok/s | |
| 17.4 GB | 17.7 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~197 tok/s | |
| 21.4 GB | 21.6 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~174 tok/s | |
| 25.3 GB | 25.6 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 25.4 GB | |
| 29.3 GB | 29.5 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 29.3 GB | |
| 35.4 GB | 35.6 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 35.5 GB | |
| 70.4 GB | 70.6 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 70.5 GB |
Selected Q4_K_M
4-bit medium quantization21.5GBat 16K context
- Weights
- 21.0 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 2.5 GB free · ~174 tok/s
≥50 tok/s needs ≥200 GB/s · RTX 5090 ~239, RTX 3090 Ti ~174
Which Hardware 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 2.6 GB, bringing total usage to 24.0 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090. 100 devices with unified memory can run MoziAI 35B A3B MOE MTP, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
Q4_K_M · best fit Q3_K_M (17.5 GB)
1 GPU
RX 7900 XT~84Simulate output on RX 7900 XT32–40 GB
fits · 10.5 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~239Simulate output on RTX 5090M5 Max36 GB~66Simulate output on Mac Studio M5 Max (36 GB)M532 GB~34Simulate output on MacBook Air 13" M5 (32 GB)Orin~51Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~33Simulate 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 |
|---|---|---|---|---|
| Qwen3.6 35B A3BAlibaba | 106.8 | 22 GB | ~151 | same size |
| MiniCPM V 4.7 35B A3BOpenBMB | — | 22.1 GB | ~169 | same size |
| Ornith 1.5 35B A3Bornith-ai | — | 22 GB | ~151 | same size |
| Agents A1InternScience | — | 21.5 GB | ~171 | same size |
| Intern S2 PreviewInternLM | — | 73.2 GB | —needs > 24 GB | same size |
| EXAONE 4.5 33BLGAI-EXAONE | — | 23.9 GB | ~33 | same size |
Specifications
- Publisher
- chenyumo
- Parameters
- 35B
- Active parameters
- 3.8B per token
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-08-10
- License
- Other
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 2.6 GB (24.0 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)
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 ≈ 3 GB (at full 262K context)
VRAM usage by quantization
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
★ Recommended — best balance of quality and VRAM usage.
Can I run MoziAI 35B A3B MOE MTP on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run MoziAI 35B A3B MOE MTP, the smallest at Q3_K_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 21.4 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M1 Max (32 GB).
Can I run MoziAI 35B A3B MOE MTP locally?
Yes — MoziAI 35B A3B MOE MTP can run locally on consumer hardware. 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 ~118 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~174 tok/s. 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 → 2.3 GB active ÷ (8000 × 0.65) = 0.446 ms, plus 40 layers × 0.055 ms = 2.200 ms, so 1000 ÷ 2.646 ms = ~378 tok/s
Estimated speed at Q4_K_M (21.4 GB)
Real-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. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
Which devices can run MoziAI 35B A3B MOE MTP?
100 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, 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.