Clover 35B A3B Preview — Hardware Requirements & GPU Compatibility
ChatFunctions
Clover 35B A3B Preview is a 34.7B-parameter open language model from Diffuspace. It supports a context window of up to 131,072 tokens. At BF16 it needs about 69.71 GB of VRAM — see which GPUs and Macs can run it below.
Clover 35B A3B Preview runs on a 96 GB+ Mac or a workstation GPU
Best local pick → Mac Studio (M3 Ultra, 96GB) · BF16 · 70.3 GB · ~50 tok/s
Macs from 96 GB (BF16 · ~50 tok/s)
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Clover 35B A3B Preview
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 Diffuspace/Clover-35B-A3B-Preview --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) (25 GB headroom) · BF16
- Generation speed
- ~122 tok/s
- generation speed
- Cost per 1M output tokens
- $2.70
- per 1M output tokens
How Much VRAM Does Clover 35B A3B Preview Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 69.7 GB | 71 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on RTX PRO 5000 Blackwell 72 GB |
Selected BF16
Brain floating point 1670.3GBat 16K context
- Weights
- 69.3 GB
- KV cache
- 0.7 GB
- Overhead
- 0.3 GB
Server-class: ~70.3 GB at 16K context · one RTX PRO 5000 Blackwell 72 GB
Or .
Which Hardware Can Run Clover 35B A3B Preview?
BF16 · 69.7 GBClover 35B A3B Preview (BF16) requires 69.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 91+ GB is recommended. Using the full 131K context window can add up to 5.3 GB, bringing total usage to 75.0 GB. No consumer GPU has enough memory. 30 devices with unified memory can run Clover 35B A3B Preview, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio (M3 Ultra, 96GB).
96 GB
fits · 25.7 GB free · up to 128K ctx
3 GPUs · 2 Mac classes
RTX PRO 6000 Blackwell Max-Q Workstation Edition~122Simulate output on RTX PRO 6000 Blackwell Max-Q Workstation EditionRTX PRO 6000 Blackwell Workstation Edition~122Simulate output on RTX PRO 6000 Blackwell Workstation EditionRTX PRO 6000 Blackwell Server Edition~112Simulate output on RTX PRO 6000 Blackwell Server EditionM3 Ultra*96 GB~50Simulate output on Mac Studio (M3 Ultra, 96GB)M3 Max*96 GB~24Simulate output on MacBook Pro 14" M3 Max (96 GB)128–144 GB
fits · 57.7 GB free · up to 128K ctx
4 GPUs · 2 Mac classes · 4 device families
GH200 Grace Hopper Superchip~228Simulate output on GH200 Grace Hopper SuperchipH200 NVL~226Simulate output on H200 NVLH200 SXM~226Simulate output on H200 SXMM2 Ultra*128 GB~49Simulate output on Mac Pro M2 Ultra (128 GB)M5 Max128 GB~41Simulate output on Mac Studio M5 Max (128 GB)GB10~24Simulate output on NVIDIA DGX SparkJetson T5000 (Thor)~24Simulate 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 ≥ 70.3 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 |
|---|---|---|---|---|
| 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
- Diffuspace
- Parameters
- 34.7B
- Active parameters
- 3.5B per token
- Architecture
- CloverMoeModelLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-10-24
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Clover 35B A3B Preview need?
Clover 35B A3B Preview requires 69.7 GB of VRAM at BF16. Full 131K context adds up to 5.3 GB (75.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 34.7B × 16 bits ÷ 8 = 69.3 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 ≈ 5.7 GB (at full 131K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Clover 35B A3B Preview?
No — Clover 35B A3B Preview requires at least 69.7 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run Clover 35B A3B Preview on a Mac?
Yes — Mac Studio (M3 Ultra, 96GB) and 20 other Macs can run Clover 35B A3B Preview. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 69.7 GB of usable unified memory (RAM minus macOS overhead).
Can I run Clover 35B A3B Preview locally?
Yes — Clover 35B A3B Preview can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Clover 35B A3B Preview?
At BF16, Clover 35B A3B Preview can reach ~106 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 → 7.0 GB active ÷ (8000 × 0.65) = 1.337 ms, plus 40 layers × 0.055 ms = 2.200 ms, so 1000 ÷ 3.537 ms = ~283 tok/s
Estimated speed at BF16 (69.7 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Clover 35B A3B Preview?
At BF16, the download is about 69.32 GB.
Which GPUs can run Clover 35B A3B Preview?
No single consumer GPU has enough VRAM to run Clover 35B A3B Preview at BF16 (69.7 GB). Multi-GPU or professional hardware is required.
Which devices can run Clover 35B A3B Preview?
30 devices with unified memory can run Clover 35B A3B Preview at BF16 (69.7 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.