Kumru 2B — Hardware Requirements & GPU Compatibility
Chat
Kumru 2B is a 2.4B-parameter open language model from vngrs-ai. It supports a context window of up to 8,192 tokens. At BF16 it needs about 5.16 GB of VRAM — see which GPUs and Macs can run it below.
1.0K downloads
114 likesSpecifications
- Publisher
- vngrs-ai
- Parameters
- 2.4B
- Architecture
- MistralForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 50,176
- Release Date
- 2025-09-26
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Kumru 2B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 5.2 GB | 5.5 GB | 4.75 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Kumru 2B?
BF16 · 5.2 GBKumru 2B (BF16) requires 5.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. Using the full 8K context window can add up to 0.3 GB, bringing total usage to 5.5 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Kumru 2B?
BF16 · 5.2 GB33 devices with unified memory can run Kumru 2B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Kumru 2B need?
Kumru 2B requires 5.2 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 2.4B × 16 bits ÷ 8 = 4.8 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 0.7 GB (at full 8K context)
VRAM usage by quantization
BF165.2 GBBF16 + full context5.5 GB- Can I run Kumru 2B on a Mac?
Kumru 2B requires at least 5.2 GB at BF16, 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 Kumru 2B locally?
Yes — Kumru 2B can run locally on consumer hardware. At BF16 quantization it needs 5.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Kumru 2B?
At BF16, Kumru 2B can reach ~565 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~127 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 5.2 × 0.55 = ~565 tok/s
Estimated speed at BF16 (5.2 GB)
~565 tok/s~127 tok/s~422 tok/s~349 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Kumru 2B?
At BF16, the download is about 4.75 GB.
- Which GPUs can run Kumru 2B?
35 consumer GPUs can run Kumru 2B at BF16 (5.2 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Kumru 2B?
33 devices with unified memory can run Kumru 2B at BF16 (5.2 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.