SmolLM2 360M — Hardware Requirements & GPU Compatibility
Chat
SmolLM2 360M is a 362M-parameter open language model from Hugging Face in the SmolLM family. It supports a context window of up to 8,192 tokens. At Q4_K_M it needs about 0.60 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 8K)Best on 24 GB (Q4_K_M · ~1092 tok/s · 8K)Macs from 8 GB (Q4_K_M · ~120 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run SmolLM2 360M
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/mradermacher/SmolLM2-360M-i1-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 23.1 GB free · 8K context
Download: SmolLM2-360M.i1-Q4_K_M.gguf0.27 GBmradermacher
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (11 GB headroom) · Q4_K_M
- Generation speed
- ~390 tok/s
- generation speed
- Cost per 1M output tokens
- $0.059
- per 1M output tokens
How Much VRAM Does SmolLM2 360M Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.5 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 8K context · ~1213 tok/s | |
| 0.5 GB | — | 3-bit small — 3-bit small quantization | Fits: 8K context · ~1213 tok/s | |
| 0.6 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 8K context · ~1170 tok/s | |
| 0.6 GB | — | 4-bit · legacy — 4-bit legacy quantization | Fits: 8K context · ~1170 tok/s | |
| 0.6 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 8K context · ~1092 tok/s | |
| 0.6 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 8K context · ~1024 tok/s | |
| 0.7 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 8K context · ~964 tok/s | |
| 0.8 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 8K context · ~874 tok/s |
Selected Q4_K_M
4-bit medium quantization0.9GBat 8K context
- Weights
- 0.2 GB
- KV cache
- 0.3 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.2 GB free · ~1092 tok/s
≥50 tok/s needs ≥46 GB/s · RTX 5090 ~1941, RTX 3090 Ti ~1092
Which Hardware Can Run SmolLM2 360M?
Q4_K_M · 0.6 GBSmolLM2 360M (Q4_K_M) requires 0.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. Using the full 8K context window can add up to 0.3 GB, bringing total usage to 0.8 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run SmolLM2 360M, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 7.2 GB free · up to 8K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~824Simulate output on RTX 3080RTX 2080 Ti~667Simulate output on RTX 2080 TiRTX 3070 Ti~659Simulate output on RTX 3070 TiM3*8 GB~120Simulate output on iMac 24" M3 (8 GB)Orin Nano~111Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~80Simulate output on iPhone 1720 GB
fits · 19.1 GB free · up to 8K ctx
1 GPU
RX 7900 XT~800Simulate output on RX 7900 XT32–40 GB
fits · 31.1 GB free · up to 8K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~1941Simulate output on RTX 5090M5 Max36 GB~537Simulate output on Mac Studio M5 Max (36 GB)M532 GB~179Simulate output on MacBook Air 13" M5 (32 GB)Orin~222Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~146Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is SmolLM2 360M?
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
Independent11.4%
#142/145 open
Alternatives to SmolLM2 360M
SmolLM family · 15 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Granite 4.0 350MIBM | — | 1 GB | ~1150 | same size |
| LFM2.5 350MLiquid AI | — | 0.8 GB | ~1130 | same size |
| ERNIE 4.5 0.3B PTBaidu | — | 0.7 GB | ~1213 | same size |
| Opt 350MMeta | — | 0.8 GB | ~851 | same size |
| Codegen 350M MonoSalesforce | — | 0.8 GB | ~851 | same size |
| Gpt2 MediumOpenAI | — | 0.3 GB | ~2621 | same size |
Fine-tunes & variants(2)
Specifications
- Publisher
- Hugging Face
- Family
- SmolLM
- Parameters
- 362M
- Architecture
- LlamaForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 49,152
- Release Date
- 2024-10-31
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does SmolLM2 360M need?
SmolLM2 360M requires 0.6 GB of VRAM at Q4_K_M, or 1.1 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 362M × 4.8 bits ÷ 8 = 0.2 GB
KV Cache + Overhead ≈ 0.4 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 ≈ 0.6 GB (at full 8K context)
VRAM usage by quantization
What's the best quantization for SmolLM2 360M?
For SmolLM2 360M, Q4_K_M (0.6 GB) offers the best balance of quality and VRAM usage. Q5_K_S (0.6 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 0.5 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run SmolLM2 360M on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run SmolLM2 360M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run SmolLM2 360M locally?
Yes — SmolLM2 360M can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is SmolLM2 360M?
At Q4_K_M, SmolLM2 360M can reach ~8000 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1092 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 ÷ 0.6 × 0.65 = ~8667 tok/s
Estimated speed at Q4_K_M (0.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of SmolLM2 360M?
At Q4_K_M, the download is about 0.22 GB. The full-precision BF16 version is 0.72 GB. The smallest option (IQ2_XXS) is 0.10 GB.
Which GPUs can run SmolLM2 360M?
52 consumer GPUs can run SmolLM2 360M 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 360M?
163 devices with unified memory can run SmolLM2 360M at Q4_K_M (0.6 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.