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.
633 downloads
20 likesSpecifications
- Publisher
- elte-nlp
- Parameters
- 4.0B
- Release Date
- 2025-09-12
- License
- CC BY-NC-SA 4.0
Get Started
HuggingFace
How Much VRAM Does Racka 4B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 1.9 GB | — | 1.71 GB | 2-bit quantization with K-quant improvements |
| IQ3_S | 3.40 | 1.9 GB | — | 1.71 GB | Importance-weighted 3-bit, small |
| Q3_K_Mest. | 3.90 | 2.2 GB | — | 1.96 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 2.6 GB | — | 2.41 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 3.1 GB | — | 2.87 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 3.6 GB | — | 3.32 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 4.4 GB | — | 4.02 GB | 8-bit quantization, near-lossless |
| BF16 | 16.00 | 8.8 GB | — | 8.04 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 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. 50 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Racka 4B?
Q4_K_M · 2.6 GB59 devices with unified memory can run Racka 4B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download Racka 4B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
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)
VRAM usage by quantization
Q4_K_M2.6 GB- 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 Q2_K at 1.9 GB.
VRAM requirement by quantization
Q2_K1.9 GBQ3_K_M2.2 GBQ4_K_M ★2.6 GBQ5_K_M3.1 GBQ6_K3.6 GBBF168.8 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Racka 4B on a Mac?
Racka 4B requires at least 1.9 GB at Q2_K, 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 Racka 4B locally?
Yes — Racka 4B can run locally on consumer hardware. At Q4_K_M quantization it needs 2.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Racka 4B?
At Q4_K_M, Racka 4B can reach ~1660 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 ÷ 2.6 × 0.65 = ~1962 tok/s
Estimated speed at Q4_K_M (2.6 GB)
~1962 tok/s~247 tok/s~1962 tok/s~1660 tok/sReal-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 (Q2_K) is 1.71 GB.
- Which GPUs can run Racka 4B?
50 consumer GPUs can run Racka 4B at Q4_K_M (2.6 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 50 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Racka 4B?
59 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, 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.