K2 Horizon 375B A23B — Hardware Requirements & GPU Compatibility
Chat
K2 Horizon 375B A23B is a 379.2B-parameter open language model from IFM. It supports a context window of up to 524,288 tokens. At BF16 it needs about 759.15 GB of VRAM — see which GPUs and Macs can run it below.
K2 Horizon 375B A23B runs on a multi-GPU server
BF16 needs ~762.7 GB · about 7× H200 SXM 141 GB
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run K2 Horizon 375B A23B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve IFM/K2-Horizon-375B-A23B --max-model-len 16384 --tensor-parallel-size 8Size the nodes from the table above
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Rent 7× H200 SXM · BF16
- Estimated hourly price
- ~$25.13/hr
- est., whole server
- GPUs
- 7 GPUs
- 987 GB of VRAM
How Much VRAM Does K2 Horizon 375B A23B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 759.1 GB | 766.8 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on 7× H200 SXM 141 GB |
Selected BF16
Brain floating point 16762.7GBat 16K context
- Weights
- 758.3 GB
- KV cache
- 4.1 GB
- Overhead
- 0.3 GB
Server-class: ~762.7 GB at 16K context · about 7× H200 SXM 141 GB
Which Hardware Can Run K2 Horizon 375B A23B?
BF16 · 759.1 GBK2 Horizon 375B A23B (BF16) requires 759.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 987+ GB is recommended. Using the full 524K context window can add up to 130.5 GB, bringing total usage to 889.6 GB. No consumer GPU has enough memory.
Needs server-class hardware
K2 Horizon 375B A23B runs on a multi-GPU server · BF16 needs ~762.7 GB
| Hardware | Quant | Memory | Context | Hardware page | |
|---|---|---|---|---|---|
| 7× H200 SXM 141 GB · 987 GB | BF16 | 762.7 GB | 256K ctx | H200 SXM → | BF16 · 762.7 GB · 256K ctx |
| 5× B200 192 GB · 960 GB | BF16 | 762.7 GB | 256K ctx | B200 → | BF16 · 762.7 GB · 256K ctx |
By VRAM tier · typical GPUs and Macs at BF16
Consumer GPUs (up to 32 GB) and Macs up to 512 GB: too small for this model (needs ≥ 762.7 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 |
|---|---|---|---|---|
| Qwen3.5 397B A17BAlibaba | 113.0 | 242.6 GB | —needs > 24 GB | same size |
| GLM 4.6Z.ai | 103.1 | 216.9 GB | —needs > 24 GB | same size |
| Llama 4 Maverick 17B 128E InstructMeta | 87.1 | 272.7 GB | —needs > 24 GB | same size |
| Llama 3.1 405B InstructMeta | 83.2 | 275.6 GB | —needs > 24 GB | same size |
| Intern S2 397BInternLM | — | 242.6 GB | —needs > 24 GB | same size |
| Ornith 1.5 397Bornith-ai | — | 242.6 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- IFM
- Parameters
- 379.2B
- Active parameters
- 26.7B per token
- Architecture
- K2HorizonForCausalLM
- Context Length
- 524,288 tokens
- Vocabulary Size
- 250,624
- Release Date
- 2026-09-01
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does K2 Horizon 375B A23B need?
K2 Horizon 375B A23B requires 759.1 GB of VRAM at BF16. Full 524K context adds up to 130.5 GB (889.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 379.2B × 16 bits ÷ 8 = 758.3 GB
KV Cache + Overhead ≈ 0.9 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 ≈ 131.3 GB (at full 524K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run K2 Horizon 375B A23B?
No — K2 Horizon 375B A23B requires at least 759.1 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run K2 Horizon 375B A23B on a Mac?
K2 Horizon 375B A23B requires at least 759.1 GB at BF16. None of the 146 Macs we list has that much usable memory (the largest has 508.5 GB after macOS overhead).
Can I run K2 Horizon 375B A23B locally?
Yes — K2 Horizon 375B A23B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of K2 Horizon 375B A23B?
At BF16, the download is about 758.33 GB.
Which GPUs can run K2 Horizon 375B A23B?
No single consumer GPU has enough VRAM to run K2 Horizon 375B A23B at BF16 (759.1 GB). Multi-GPU or professional hardware is required.
Which devices can run K2 Horizon 375B A23B?
K2 Horizon 375B A23B requires at least 759.1 GB at BF16, which exceeds the usable memory of every unified-memory device we list (the largest has 508.5 GB).