Protgpt2 Distilled Tiny — Hardware Requirements & GPU Compatibility
Chat
Protgpt2 Distilled Tiny is a 39M-parameter open language model from littleworth. It supports a context window of up to 1,024 tokens. At Q4_K_M it needs about 0.03 GB of VRAM — see which GPUs and Macs can run it below.
169 downloads
5 likesSpecifications
- Publisher
- littleworth
- Parameters
- 39M
- Architecture
- GPT2LMHeadModel
- Context Length
- 1,024 tokens
- Vocabulary Size
- 50,257
- Release Date
- 2026-02-25
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Protgpt2 Distilled Tiny Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q4_0 | 4.00 | 0.0 GB | — | 0.02 GB | 4-bit legacy quantization |
| Q3_K_S | 3.50 | 0.0 GB | — | 0.02 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 0.0 GB | — | 0.02 GB | 3-bit medium quantization |
| Q2_K | 3.40 | 0.0 GB | — | 0.02 GB | 2-bit quantization with K-quant improvements |
| Q4_K_M | 4.80 | 0.0 GB | — | 0.02 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 0.0 GB | — | 0.03 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 0.0 GB | — | 0.03 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 0.0 GB | — | 0.04 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Protgpt2 Distilled Tiny?
Q4_K_M · 0.0 GBProtgpt2 Distilled Tiny (Q4_K_M) requires 0.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Protgpt2 Distilled Tiny?
Q4_K_M · 0.0 GB33 devices with unified memory can run Protgpt2 Distilled Tiny, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Protgpt2 Distilled Tiny need?
Protgpt2 Distilled Tiny requires 0.0 GB of VRAM at Q4_K_M, or 0.0 GB at Q8_0.
VRAM = Weights + KV Cache + Overhead
Weights = 39M × 4.8 bits ÷ 8 = 0 GB
VRAM usage by quantization
Q4_K_M0.0 GB- What's the best quantization for Protgpt2 Distilled Tiny?
For Protgpt2 Distilled Tiny, Q4_K_M (0.0 GB) offers the best balance of quality and VRAM usage. Q5_1 (0.0 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XS at 0.0 GB.
VRAM requirement by quantization
IQ3_XS0.0 GBIQ4_XS0.0 GBQ2_K0.0 GBQ4_K_M ★0.0 GBQ5_K_S0.0 GBQ8_00.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Protgpt2 Distilled Tiny on a Mac?
Protgpt2 Distilled Tiny requires at least 0.0 GB at IQ3_XS, 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 Protgpt2 Distilled Tiny locally?
Yes — Protgpt2 Distilled Tiny can run locally on consumer hardware. At Q4_K_M quantization it needs 0.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Protgpt2 Distilled Tiny?
At Q4_K_M, Protgpt2 Distilled Tiny can reach ~97167 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~21840 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 ÷ 0.0 × 0.55 = ~97167 tok/s
Estimated speed at Q4_K_M (0.0 GB)
~97167 tok/s~21840 tok/s~72627 tok/s~60075 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Protgpt2 Distilled Tiny?
At Q4_K_M, the download is about 0.02 GB. The full-precision Q8_0 version is 0.04 GB. The smallest option (IQ3_XS) is 0.02 GB.
- Which GPUs can run Protgpt2 Distilled Tiny?
35 consumer GPUs can run Protgpt2 Distilled Tiny at Q4_K_M (0.0 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 Protgpt2 Distilled Tiny?
33 devices with unified memory can run Protgpt2 Distilled Tiny at Q4_K_M (0.0 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.