SmolLM2 1.7B — Hardware Requirements & GPU Compatibility
Chat
SmolLM2 1.7B is the base pretrained model from Hugging Face's second-generation SmolLM family. Unlike the instruct variant, this model has not been fine-tuned for chat or instruction following, making it a strong foundation for custom fine-tuning, domain adaptation, or research into small-scale language model behavior. At 1.7 billion parameters, it provides meaningful language understanding and generation capabilities while remaining lightweight enough to train and experiment with on consumer hardware. Researchers and developers who want full control over downstream behavior will find this base model more flexible than the instruction-tuned version.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 8K)Best on 24 GB (Q4_K_M · ~379 tok/s · 8K)Macs from 8 GB (Q4_K_M · ~41 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run SmolLM2 1.7B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/mradermacher/SmolLM2-1.7B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 21.1 GB free · 8K context
Download: SmolLM2-1.7B.Q4_K_M.gguf1.06 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3060 12GB (9 GB headroom) · Q4_K_M
- Generation speed
- ~135 tok/s
- generation speed
- Cost per 1M output tokens
- $0.12
- per 1M output tokens
How Much VRAM Does SmolLM2 1.7B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.4 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 8K context · ~458 tok/s | |
| 1.4 GB | — | 3-bit small — 3-bit small quantization | Fits: 8K context · ~452 tok/s | |
| 1.5 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 8K context · ~426 tok/s | |
| 1.6 GB | — | 3-bit large — 3-bit large quantization | Fits: 8K context · ~415 tok/s | |
| 1.7 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 8K context · ~379 tok/s | |
| 1.9 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 8K context · ~341 tok/s | |
| 2.1 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 8K context · ~311 tok/s | |
| 2.4 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 8K context · ~272 tok/s |
Selected Q4_K_M
4-bit medium quantization2.9GBat 8K context
- Weights
- 1.0 GB
- KV cache
- 1.6 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.1 GB free · ~379 tok/s
≥50 tok/s needs ≥133 GB/s · RTX 5090 ~673, RTX 3090 Ti ~379
Which Hardware Can Run SmolLM2 1.7B?
Q4_K_M · 1.7 GBSmolLM2 1.7B (Q4_K_M) requires 1.7 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 8K context window can add up to 1.2 GB, bringing total usage to 2.9 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run SmolLM2 1.7B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.1 GB free · up to 8K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~286Simulate output on RTX 3080RTX 2080 Ti~231Simulate output on RTX 2080 TiRTX 3070 Ti~229Simulate output on RTX 3070 TiM3*8 GB~41Simulate output on iMac 24" M3 (8 GB)Orin Nano~38Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~28Simulate output on iPhone 1720 GB
fits · 17.1 GB free · up to 8K ctx
1 GPU
RX 7900 XT~278Simulate output on RX 7900 XT32–40 GB
fits · 29.1 GB free · up to 8K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~673Simulate output on RTX 5090M5 Max36 GB~186Simulate output on Mac Studio M5 Max (36 GB)M532 GB~62Simulate output on MacBook Air 13" M5 (32 GB)Orin~77Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~51Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is SmolLM2 1.7B?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
This is the single board showing results for this model; badges show who ran the test.
- MMLU-Pro
TIGER-LabIndependent
Independent18.3%
#133/146 open
Alternatives to SmolLM2 1.7B
SmolLM family · 15 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| LFM3 1.7BLiquid AI | — | 2.1 GB | ~455 | same size |
| Granite 4.0 1BIBM | — | 2.6 GB | ~452 | same size |
| LFM2 VL 1.6BLiquid AI | — | 1.5 GB | ~496 | same size |
| Qwen 1 8BAlibaba | — | 1.9 GB | ~542 | same size |
| JiRackUltra 1BCMSManhattan | — | 1.8 GB | ~461 | same size |
| Qwen3 1.7B BaseAlibaba | — | 3.2 GB | ~417 | same size |
Fine-tunes & variants(1)
Specifications
- Publisher
- Hugging Face
- Family
- SmolLM
- Parameters
- 1.7B
- Architecture
- LlamaForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 49,152
- Release Date
- 2024-10-30
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does SmolLM2 1.7B need?
SmolLM2 1.7B requires 1.7 GB of VRAM at Q4_K_M, or 4.1 GB at BF16. Full 8K context adds up to 1.2 GB (2.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.7B × 4.8 bits ÷ 8 = 1 GB
KV Cache + Overhead ≈ 0.7 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.
KV Cache + Overhead ≈ 1.9 GB (at full 8K context)
VRAM usage by quantization
What's the best quantization for SmolLM2 1.7B?
For SmolLM2 1.7B, Q4_K_M (1.7 GB) offers the best balance of quality and VRAM usage. Q5_K_S (1.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run SmolLM2 1.7B on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run SmolLM2 1.7B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.7 GB of usable unified memory (RAM minus macOS overhead).
Can I run SmolLM2 1.7B locally?
Yes — SmolLM2 1.7B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is SmolLM2 1.7B?
At Q4_K_M, SmolLM2 1.7B can reach ~2775 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~379 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 ÷ 1.73 × 0.65 = ~3006 tok/s
Estimated speed at Q4_K_M (1.7 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of SmolLM2 1.7B?
At Q4_K_M, the download is about 1.03 GB. The full-precision BF16 version is 3.42 GB. The smallest option (Q2_K) is 0.73 GB.
Which GPUs can run SmolLM2 1.7B?
52 consumer GPUs can run SmolLM2 1.7B 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 SmolLM2 1.7B?
163 devices with unified memory can run SmolLM2 1.7B at Q4_K_M (1.7 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.