Holo4 35B A3B — Hardware Requirements & GPU Compatibility
VisionFunctions
Holo4-35B-A3B is H Company's mixture-of-experts vision-language model for computer use, with about 35 billion total and 3.9 billion active parameters per token, built on Qwen3.6-35B-A3B. Used with the hai-agents harness, it reads screenshots and tool results and emits clicks, typing, code and tool calls for web, desktop and mobile tasks. The card reports 30.9% on OSWorld 2.0 and 34.5% on AutomationBench, below the dense 27B sibling on both, at lower cost per task. Because only a small share of weights is active, decoding is fast, but all 35 billion parameters must still fit in memory, so a quantized copy suits a 24 GB GPU with offloading or a machine with ample unified memory. The context window is 262,144 tokens. The weights are released under the Apache 2.0 license, permitting commercial use, unlike the non-commercial Holo4-27B. It was published in September 2026, with FP8, NVFP4 and Q4 GGUF variants listed on the card.
359 downloads
25 likesSpecifications
- Publisher
- Hcompany
- Parameters
- 35.1B
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-09-24
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Holo4 35B A3B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 15.3 GB | 26.0 GB | 14.92 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 15.7 GB | 26.4 GB | 15.36 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 17.5 GB | 28.1 GB | 17.11 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 17.9 GB | 28.6 GB | 17.55 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 21.4 GB | 32.1 GB | 21.06 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 25.4 GB | 36.0 GB | 25.01 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 29.4 GB | 40 GB | 28.96 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 35.5 GB | 46.1 GB | 35.11 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Holo4 35B A3B?
Q4_K_M · 21.4 GBHolo4 35B A3B (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 32.1 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 Holo4 35B A3B?
Q4_K_M · 21.4 GB41 devices with unified memory can run Holo4 35B A3B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, NVIDIA Jetson AGX Orin 32GB.
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Holo4 35B A3B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Holo4 35B A3B need?
Holo4 35B A3B requires 21.4 GB of VRAM at Q4_K_M, or 70.6 GB at BF16. Full 262K context adds up to 10.7 GB (32.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 35.1B × 4.8 bits ÷ 8 = 21.1 GB
KV Cache + Overhead ≈ 0.3 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 context32.1 GB- Can NVIDIA GeForce RTX 4090 run Holo4 35B A3B?
Yes, at Q4_K_L (21.9 GB) or lower. Higher quantizations like Q5_K_S (24.5 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Holo4 35B A3B?
For Holo4 35B A3B, Q4_K_M (21.4 GB) offers the best balance of quality and VRAM usage. Q4_K_L (21.9 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 10.0 GB.
VRAM requirement by quantization
IQ2_XXS10.0 GBQ2_K15.3 GBQ3_K_L18.4 GBQ4_K_M ★21.4 GBQ4_K_L21.9 GBBF1670.6 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Holo4 35B A3B on a Mac?
Holo4 35B A3B requires at least 10.0 GB at IQ2_XXS, 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 Holo4 35B A3B locally?
Yes — Holo4 35B A3B 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 Holo4 35B A3B?
At Q4_K_M, Holo4 35B A3B can reach ~118 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~171 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 = ~376 tok/s
Estimated speed at Q4_K_M (21.4 GB)
~376 tok/s~171 tok/s~376 tok/s~339 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Holo4 35B A3B?
At Q4_K_M, the download is about 21.06 GB. The full-precision BF16 version is 70.21 GB. The smallest option (IQ2_XXS) is 9.65 GB.
- Which GPUs can run Holo4 35B A3B?
7 consumer GPUs can run Holo4 35B A3B at Q4_K_M (21.4 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
- Which devices can run Holo4 35B A3B?
41 devices with unified memory can run Holo4 35B A3B 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.