K2 Horizon MoVA 36B A4B — Hardware Requirements & GPU Compatibility
Chat
K2 Horizon MoVA 36B A4B is a 37.4B-parameter open language model from IFM. It supports a context window of up to 524,288 tokens. At Q4_K_M it needs about 23.02 GB of VRAM — see which GPUs and Macs can run it below.
1.3K downloads
168 likesSpecifications
- Publisher
- IFM
- Parameters
- 37.4B
- Architecture
- K2HorizonForCausalLM
- Context Length
- 524,288 tokens
- Vocabulary Size
- 250,624
- Release Date
- 2026-09-01
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does K2 Horizon MoVA 36B A4B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 16.5 GB | 80.6 GB | 15.91 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 16.9 GB | 81.1 GB | 16.38 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 18.8 GB | 83.0 GB | 18.25 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 19.3 GB | 83.5 GB | 18.72 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 23.0 GB | 87.2 GB | 22.47 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 27.2 GB | 91.4 GB | 26.68 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 31.4 GB | 95.6 GB | 30.89 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 38 GB | 102.2 GB | 37.44 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run K2 Horizon MoVA 36B A4B?
Q4_K_M · 23.0 GBK2 Horizon MoVA 36B A4B (Q4_K_M) requires 23.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 30+ GB is recommended. Using the full 524K context window can add up to 64.2 GB, bringing total usage to 87.2 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 K2 Horizon MoVA 36B A4B?
Q4_K_M · 23.0 GB41 devices with unified memory can run K2 Horizon MoVA 36B A4B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download K2 Horizon MoVA 36B A4B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Frequently Asked Questions
- How much VRAM does K2 Horizon MoVA 36B A4B need?
K2 Horizon MoVA 36B A4B requires 23.0 GB of VRAM at Q4_K_M, or 75.4 GB at BF16. Full 524K context adds up to 64.2 GB (87.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 37.4B × 4.8 bits ÷ 8 = 22.5 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 64.7 GB (at full 524K context)
VRAM usage by quantization
Q4_K_M23.0 GBQ4_K_M + full context87.2 GB- Can NVIDIA GeForce RTX 4090 run K2 Horizon MoVA 36B A4B?
Yes, at Q5_0 (23.9 GB) or lower. Higher quantizations like Q5_K_S (26.3 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for K2 Horizon MoVA 36B A4B?
For K2 Horizon MoVA 36B A4B, Q4_K_M (23.0 GB) offers the best balance of quality and VRAM usage. Q5_0 (23.9 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 10.8 GB.
VRAM requirement by quantization
IQ2_XXS10.8 GBIQ3_XS16.0 GBQ3_K_L19.7 GBQ4_K_M ★23.0 GBQ5_023.9 GBBF1675.4 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run K2 Horizon MoVA 36B A4B on a Mac?
K2 Horizon MoVA 36B A4B requires at least 10.8 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 K2 Horizon MoVA 36B A4B locally?
Yes — K2 Horizon MoVA 36B A4B can run locally on consumer hardware. At Q4_K_M quantization it needs 23.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is K2 Horizon MoVA 36B A4B?
At Q4_K_M, K2 Horizon MoVA 36B A4B can reach ~209 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~29 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 ÷ 23.0 × 0.65 = ~226 tok/s
Estimated speed at Q4_K_M (23.0 GB)
~226 tok/s~29 tok/s~226 tok/s~209 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of K2 Horizon MoVA 36B A4B?
At Q4_K_M, the download is about 22.47 GB. The full-precision BF16 version is 74.89 GB. The smallest option (IQ2_XXS) is 10.30 GB.
- Which GPUs can run K2 Horizon MoVA 36B A4B?
7 consumer GPUs can run K2 Horizon MoVA 36B A4B at Q4_K_M (23.0 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
- Which devices can run K2 Horizon MoVA 36B A4B?
41 devices with unified memory can run K2 Horizon MoVA 36B A4B at Q4_K_M (23.0 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.