SmolLM3 3B Base — Hardware Requirements & GPU Compatibility
Chat
SmolLM3 3B Base is the pretrained foundation model from Hugging Face's third-generation SmolLM family. Without instruction tuning or chat alignment, it serves as a versatile starting point for researchers and developers who want to fine-tune the model for specific domains, tasks, or behavioral profiles. With 3 billion parameters and the architectural improvements introduced in SmolLM3, this base model offers strong general language capabilities in a package that remains practical to train and adapt on consumer-grade hardware. It is an excellent choice for custom fine-tuning projects where off-the-shelf chat behavior is not needed.
89.8K downloads
150 likesSpecifications
- Publisher
- Hugging Face
- Family
- SmolLM
- Parameters
- 3B
- Architecture
- SmolLM3ForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 128,256
- Release Date
- 2025-06-19
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does SmolLM3 3B Base Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 1.7 GB | 6.4 GB | 1.27 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 1.8 GB | 6.4 GB | 1.31 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 1.9 GB | 6.6 GB | 1.46 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 1.9 GB | 6.6 GB | 1.50 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 2.3 GB | 6.9 GB | 1.80 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 2.6 GB | 7.3 GB | 2.14 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 2.9 GB | 7.6 GB | 2.48 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 3.5 GB | 8.1 GB | 3.00 GB | 8-bit quantization, near-lossless |
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 SmolLM3 3B Base?
Q4_K_M · 2.3 GBSmolLM3 3B Base (Q4_K_M) requires 2.3 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 66K context window can add up to 4.7 GB, bringing total usage to 6.9 GB. 50 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run SmolLM3 3B Base?
Q4_K_M · 2.3 GB59 devices with unified memory can run SmolLM3 3B Base, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download SmolLM3 3B Base
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 SmolLM3 3B Base need?
SmolLM3 3B Base requires 2.3 GB of VRAM at Q4_K_M, or 6.5 GB at BF16. Full 66K context adds up to 4.7 GB (6.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3B × 4.8 bits ÷ 8 = 1.8 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 5.1 GB (at full 66K context)
VRAM usage by quantization
Q4_K_M2.3 GBQ4_K_M + full context6.9 GB- What's the best quantization for SmolLM3 3B Base?
For SmolLM3 3B Base, Q4_K_M (2.3 GB) offers the best balance of quality and VRAM usage. Q5_K_S (2.5 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 1.3 GB.
VRAM requirement by quantization
IQ2_XXS1.3 GBIQ3_XS1.7 GBQ4_01.9 GBIQ4_NL2.1 GBQ4_K_M ★2.3 GBBF166.5 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run SmolLM3 3B Base on a Mac?
SmolLM3 3B Base requires at least 1.3 GB at IQ2_XXS, 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 SmolLM3 3B Base locally?
Yes — SmolLM3 3B Base can run locally on consumer hardware. At Q4_K_M quantization it needs 2.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is SmolLM3 3B Base?
At Q4_K_M, SmolLM3 3B Base can reach ~1956 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~291 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 ÷ 2.3 × 0.65 = ~2311 tok/s
Estimated speed at Q4_K_M (2.3 GB)
~2311 tok/s~291 tok/s~2311 tok/s~1956 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of SmolLM3 3B Base?
At Q4_K_M, the download is about 1.80 GB. The full-precision BF16 version is 6.00 GB. The smallest option (IQ2_XXS) is 0.83 GB.
- Which GPUs can run SmolLM3 3B Base?
50 consumer GPUs can run SmolLM3 3B Base at Q4_K_M (2.3 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 SmolLM3 3B Base?
59 devices with unified memory can run SmolLM3 3B Base at Q4_K_M (2.3 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.