A.X K2 — Hardware Requirements & GPU Compatibility
Chat
A.X K2 is a 691.7B-parameter open language model from skt. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 418.90 GB of VRAM — see which GPUs and Macs can run it below.
134.1K downloads
106 likesSpecifications
- Publisher
- skt
- Parameters
- 691.7B
- Architecture
- AXK2ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 163,840
- Release Date
- 2026-07-28
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does A.X K2 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 297.9 GB | 752.8 GB | 293.97 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 341.1 GB | 796.0 GB | 337.20 GB | 3-bit medium quantization |
| IQ4_XS | 4.30 | 375.7 GB | 830.6 GB | 371.78 GB | Importance-weighted 4-bit, compact |
| Q4_K_Mest. | 4.80 | 418.9 GB | 873.8 GB | 415.01 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 496.7 GB | 951.6 GB | 492.83 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 574.5 GB | 1029.4 GB | 570.64 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 695.6 GB | 1150.5 GB | 691.69 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 1387.3 GB | 1842.2 GB | 1383.38 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 A.X K2?
Q4_K_M · 418.9 GBA.X K2 (Q4_K_M) requires 418.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 545+ GB is recommended. Using the full 262K context window can add up to 454.9 GB, bringing total usage to 873.8 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run A.X K2?
Q4_K_M · 418.9 GB2 devices with unified memory can run A.X K2, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download A.X K2
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 A.X K2 need?
A.X K2 requires 418.9 GB of VRAM at Q4_K_M, or 1387.3 GB at BF16. Full 262K context adds up to 454.9 GB (873.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 691.7B × 4.8 bits ÷ 8 = 415 GB
KV Cache + Overhead ≈ 3.9 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 458.8 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M418.9 GBQ4_K_M + full context873.8 GB- Can NVIDIA GeForce RTX 5090 run A.X K2?
No — A.X K2 requires at least 297.9 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for A.X K2?
For A.X K2, Q4_K_M (418.9 GB) offers the best balance of quality and VRAM usage. Q5_K_M (496.7 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 297.9 GB.
VRAM requirement by quantization
Q2_K297.9 GBIQ4_XS375.7 GBQ4_K_M ★418.9 GBQ5_K_M496.7 GBQ6_K574.5 GBBF161387.3 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run A.X K2 on a Mac?
A.X K2 requires at least 297.9 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 A.X K2 locally?
Yes — A.X K2 can run locally on consumer hardware. At Q4_K_M quantization it needs 418.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- What's the download size of A.X K2?
At Q4_K_M, the download is about 415.01 GB. The full-precision BF16 version is 1383.38 GB. The smallest option (Q2_K) is 293.97 GB.
- Which GPUs can run A.X K2?
No single consumer GPU has enough VRAM to run A.X K2 at Q4_K_M (418.9 GB). Multi-GPU or professional hardware is required.
- Which devices can run A.X K2?
3 devices with unified memory can run A.X K2 at Q4_K_M (418.9 GB), including Mac Studio (M3 Ultra, 512GB), NVIDIA DGX A100 640GB, NVIDIA DGX H100. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.