Smol Llama 101M GQA — Hardware Requirements & GPU Compatibility
Chat
Smol Llama 101M GQA is a 101M-parameter open language model from BEE-spoke-data in the Llama family. It supports a context window of up to 1,024 tokens. At BF16 it needs about 0.52 GB of VRAM — see which GPUs and Macs can run it below.
1.9K downloads
33 likesSpecifications
- Publisher
- BEE-spoke-data
- Family
- Llama
- Parameters
- 101M
- Architecture
- LlamaForCausalLM
- Context Length
- 1,024 tokens
- Vocabulary Size
- 32,128
- Release Date
- 2025-12-29
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Smol Llama 101M GQA Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 0.5 GB | — | 0.20 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Smol Llama 101M GQA?
BF16 · 0.5 GBSmol Llama 101M GQA (BF16) requires 0.5 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 Smol Llama 101M GQA?
BF16 · 0.5 GB33 devices with unified memory can run Smol Llama 101M GQA, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Smol Llama 101M GQA need?
Smol Llama 101M GQA requires 0.5 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 101M × 16 bits ÷ 8 = 0.2 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF160.5 GB- Can I run Smol Llama 101M GQA on a Mac?
Smol Llama 101M GQA requires at least 0.5 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 Smol Llama 101M GQA locally?
Yes — Smol Llama 101M GQA can run locally on consumer hardware. At BF16 quantization it needs 0.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Smol Llama 101M GQA?
At BF16, Smol Llama 101M GQA can reach ~5606 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~1260 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 ÷ 0.5 × 0.55 = ~5606 tok/s
Estimated speed at BF16 (0.5 GB)
~5606 tok/s~1260 tok/s~4190 tok/s~3466 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Smol Llama 101M GQA?
At BF16, the download is about 0.20 GB.
- Which GPUs can run Smol Llama 101M GQA?
35 consumer GPUs can run Smol Llama 101M GQA at BF16 (0.5 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 Smol Llama 101M GQA?
33 devices with unified memory can run Smol Llama 101M GQA at BF16 (0.5 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.