Racka 4B — Hardware Requirements & GPU Compatibility
Chat
Racka 4B is a 4.0B-parameter open language model from elte-nlp. At Q4_K_M it needs about 2.65 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 · 32K)Best on 24 GB (Q4_K_M · ~247 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~27 tok/s)
CC BY-NC-SA 4.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Racka 4B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/elte-nlp/Racka-4B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 19.2 GB free · 16K context
Download: Racka-4B-Q4_K_M-noreason.gguf2.50 GBelte-nlp
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (7 GB headroom) · Q4_K_M
- Generation speed
- ~88 tok/s
- generation speed
- Cost per 1M output tokens
- $0.26
- per 1M output tokens
How Much VRAM Does Racka 4B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.9 GB | 6.4 GB | 3-bit · i-quant small — Importance-weighted 3-bit, small | Fits: 32K context · ~349 tok/s | |
| 1.9 GB | 6.4 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~349 tok/s | |
| 2.2 GB | 6.7 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~303 tok/s | |
| 2.6 GB | 7.2 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~247 tok/s | |
| 3.1 GB | 7.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~208 tok/s | |
| 3.6 GB | 8.2 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~180 tok/s | |
| 4.4 GB | 9 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~148 tok/s | |
| 8.8 GB | 13.4 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~74 tok/s |
Selected Q4_K_M
4-bit medium quantization4.8GBat 16K context
- Weights
- 2.1 GB
- KV cache
- 2.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 19.2 GB free · ~247 tok/s
≥50 tok/s needs ≥204 GB/s · RTX 5090 ~440, RTX 3090 Ti ~247
Which Hardware Can Run Racka 4B?
Q4_K_M · 2.6 GBRacka 4B (Q4_K_M) requires 2.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Racka 4B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 3.2 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~187Simulate output on RTX 3080RTX 2080 Ti~151Simulate output on RTX 2080 TiRTX 3070 Ti~149Simulate output on RTX 3070 TiM3*8 GB~27Simulate output on iMac 24" M3 (8 GB)Orin Nano~25Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~18Simulate output on iPhone 1720 GB
fits · 15.2 GB free · up to 32K ctx
1 GPU
RX 7900 XT~181Simulate output on RX 7900 XT32–40 GB
fits · 27.2 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~440Simulate output on RTX 5090M5 Max36 GB~122Simulate output on Mac Studio M5 Max (36 GB)M532 GB~41Simulate output on MacBook Air 13" M5 (32 GB)Orin~50Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~33Simulate 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 |
|---|---|---|---|---|
| Gemma 3 4B ITGoogle | 64.0 | 5 GB | ~231 | same size |
| Granite Vision 4.1 4BIBM | — | 4 GB | ~228 | same size |
| Qwen3 4B Instruct 2507Alibaba | — | 4.2 GB | ~226 | same size |
| MiniCPM V 4OpenBMB | — | 3.1 GB | ~236 | same size |
| Phi 4 Mini ReasoningMicrosoft | — | 4.8 GB | ~228 | same size |
| Qwen2.5 VL 3B InstructAlibaba | — | 3.2 GB | ~249 | same size |
Frequently Asked Questions
How much VRAM does Racka 4B need?
Racka 4B requires 2.6 GB of VRAM at Q4_K_M, or 8.8 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 4.0B × 4.8 bits ÷ 8 = 2.4 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.
VRAM usage by quantization
What's the best quantization for Racka 4B?
For Racka 4B, Q4_K_M (2.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (3.1 GB) provides better quality if you have the VRAM. The smallest option is IQ3_S at 1.9 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Racka 4B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Racka 4B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run Racka 4B locally?
Yes — Racka 4B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Racka 4B?
At Q4_K_M, Racka 4B can reach ~1811 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~247 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 ÷ 2.65 × 0.65 = ~1962 tok/s
Estimated speed at Q4_K_M (2.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Racka 4B?
At Q4_K_M, the download is about 2.41 GB. The full-precision BF16 version is 8.04 GB. The smallest option (IQ3_S) is 1.71 GB.
Which GPUs can run Racka 4B?
52 consumer GPUs can run Racka 4B 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 Racka 4B?
163 devices with unified memory can run Racka 4B at Q4_K_M (2.6 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.