K2 Type 0.9B — Hardware Requirements & GPU Compatibility
ChatFunctions
K2 Type 0.9B is a 1.1B-parameter open language model from IFM. It supports a context window of up to 131,072 tokens. At BF16 it needs about 2.54 GB of VRAM — see which GPUs and Macs can run it below.
1.7K downloads
32 likesSpecifications
- Publisher
- IFM
- Parameters
- 1.1B
- Architecture
- K2HorizonForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 64,256
- Release Date
- 2026-09-26
- License
- Apache 2.0
Get Started
HuggingFace
Run in cloud
Fits on RTX 3060 12GB (9 GB headroom) · BF16
- Generation speed
- ~92 tok/s
- generation speed
- Cost per 1M output tokens
- $0.18
- per 1M output tokens
How Much VRAM Does K2 Type 0.9B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 2.5 GB | 8.1 GB | 2.16 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 K2 Type 0.9B?
BF16 · 2.5 GBK2 Type 0.9B (BF16) requires 2.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 131K context window can add up to 5.6 GB, bringing total usage to 8.1 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run K2 Type 0.9B?
BF16 · 2.5 GB59 devices with unified memory can run K2 Type 0.9B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does K2 Type 0.9B need?
K2 Type 0.9B requires 2.5 GB of VRAM at BF16. Full 131K context adds up to 5.5 GB (8.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.1B × 16 bits ÷ 8 = 2.2 GB
KV Cache + Overhead ≈ 0.3 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 ≈ 5.9 GB (at full 131K context)
VRAM usage by quantization
BF162.5 GBBF16 + full context8.1 GB- Can I run K2 Type 0.9B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 38 other Macs can run K2 Type 0.9B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 2.5 GB of usable unified memory (RAM minus macOS overhead).
- Can I run K2 Type 0.9B locally?
Yes — K2 Type 0.9B can run locally on consumer hardware. At BF16 quantization it needs 2.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is K2 Type 0.9B?
At BF16, K2 Type 0.9B can reach ~1890 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~258 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 ÷ 2.54 × 0.65 = ~2047 tok/s
Estimated speed at BF16 (2.5 GB)
~2047 tok/s~258 tok/s~2047 tok/s~1890 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of K2 Type 0.9B?
At BF16, the download is about 2.16 GB.
- Which GPUs can run K2 Type 0.9B?
52 consumer GPUs can run K2 Type 0.9B at BF16 (2.5 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
- Which devices can run K2 Type 0.9B?
59 devices with unified memory can run K2 Type 0.9B at BF16 (2.5 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.