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 Q4_K_M it needs about 1.84 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 8K)Best on 24 GB (Q4_K_M · ~356 tok/s · 8K)Macs from 8 GB (Q4_K_M · ~39 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Kumru 2B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve vngrs-ai/Kumru-2B --max-model-len 8192vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (9 GB headroom) · Q4_K_M
- Generation speed
- ~127 tok/s
- generation speed
- Cost per 1M output tokens
- $0.18
- per 1M output tokens
How Much VRAM Does Kumru 2B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.4 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 8K context · ~461 tok/s | |
| 1.6 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 8K context · ~417 tok/s | |
| 1.8 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 8K context · ~356 tok/s | |
| 2.1 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 8K context · ~311 tok/s | |
| 2.4 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 8K context · ~277 tok/s | |
| 2.8 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 8K context · ~235 tok/s | |
| 5.2 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 8K context · ~127 tok/s |
Selected Q4_K_M
4-bit medium quantization2.2GBat 8K context
- Weights
- 1.4 GB
- KV cache
- 0.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.8 GB free · ~356 tok/s
≥50 tok/s needs ≥141 GB/s · RTX 5090 ~633, RTX 3090 Ti ~356
Which Hardware Can Run Kumru 2B?
Q4_K_M · 1.8 GBKumru 2B (Q4_K_M) requires 1.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 8K context window can add up to 0.3 GB, bringing total usage to 2.2 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Kumru 2B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.8 GB free · up to 8K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~269Simulate output on RTX 3080RTX 2080 Ti~218Simulate output on RTX 2080 TiRTX 3070 Ti~215Simulate output on RTX 3070 TiM3*8 GB~39Simulate output on iMac 24" M3 (8 GB)Orin Nano~36Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~26Simulate output on iPhone 1720 GB
fits · 17.8 GB free · up to 8K ctx
1 GPU
RX 7900 XT~261Simulate output on RX 7900 XT32–40 GB
fits · 29.8 GB free · up to 8K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~633Simulate output on RTX 5090M5 Max36 GB~175Simulate output on Mac Studio M5 Max (36 GB)M532 GB~58Simulate output on MacBook Air 13" M5 (32 GB)Orin~72Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~48Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM5 2BOpenBMB | — | 2.5 GB | ~345 | same size |
| North Micro Vision InstructCohere | — | 7.1 GB | ~119 | same size |
| Qwen3.5 2BAlibaba | — | 1.9 GB | ~370 | same size |
| Granite 3.1 2B InstructIBM | — | 3.2 GB | ~329 | same size |
| Qwen2 VL 2B InstructAlibaba | — | 2.1 GB | ~390 | same size |
| Kimi K3 DSparkRadixArk | — | 2.2 GB | ~381 | same size |
Specifications
- Publisher
- vngrs-ai
- Parameters
- 2.4B
- Architecture
- MistralForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 50,176
- Release Date
- 2025-09-23
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Kumru 2B need?
Kumru 2B requires 1.8 GB of VRAM at Q4_K_M, or 5.2 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 2.4B × 4.8 bits ÷ 8 = 1.4 GB
KV Cache + Overhead ≈ 0.4 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 ≈ 0.8 GB (at full 8K context)
VRAM usage by quantization
What's the best quantization for Kumru 2B?
For Kumru 2B, Q4_K_M (1.8 GB) offers the best balance of quality and VRAM usage. Q5_K_M (2.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Kumru 2B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Kumru 2B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Kumru 2B locally?
Yes — Kumru 2B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Kumru 2B?
At Q4_K_M, Kumru 2B can reach ~2609 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~356 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 ÷ 1.84 × 0.65 = ~2826 tok/s
Estimated speed at Q4_K_M (1.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Kumru 2B?
At Q4_K_M, the download is about 1.43 GB. The full-precision BF16 version is 4.75 GB. The smallest option (Q2_K) is 1.01 GB.
Which GPUs can run Kumru 2B?
52 consumer GPUs can run Kumru 2B at Q4_K_M. 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 Kumru 2B?
163 devices with unified memory can run Kumru 2B at Q4_K_M (1.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.