Hugging FaceSmolLMLlamaForCausalLM

SmolLM2 135M Instruct — Hardware Requirements & GPU Compatibility

Chat

SmolLM2 135M Instruct is the instruction-tuned variant of Hugging Face's 135-million-parameter SmolLM2 model. Fine-tuned to follow user prompts and engage in basic conversational exchanges, it delivers surprisingly coherent responses given its minimal size, making it ideal for testing chat interfaces or running on extremely constrained devices. This model is a practical choice when you need an instruction-following model that fits comfortably in under 1 GB of memory. It works well for simple question answering, text reformatting, and lightweight assistant tasks where response quality can be traded for instant inference speed.

135M params · dense8K contextApache 2.0Oct 2024839.0K downloads471 likes181.4K quant downloads

Based on SmolLM2 135M

Your hardware

Verdicts below are for the reference RTX 4090. Set yours to personalise the page.

Detection reads your browser's GPU name with no data sent anywhere.

Runs great on a 24 GB GPU

Runs from 8 GB (Q4_K_M · 8K)Best on 24 GB (Q4_K_M · ~1524 tok/s · 8K)Macs from 8 GB (Q4_K_M · ~167 tok/s)

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run SmolLM2 135M Instruct

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.

Ways to runOther ways

each opens step-by-step

Run 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

Run SmolLM2 135M Instruct

0.6 GB VRAM at 8K context · fits the RTX 4090 (23.4 GB free)

Works on macOS, Windows and Linux.

Install Ollama (Linux)
$curl -fsSL https://ollama.com/install.sh | sh
Install Ollama (macOS / Windows)
Download and run the app; it installs the ollama command.
Download Ollama ↗
Run Q4_K_M
$ollama run smollm2:135m-instruct-q4_K_M
Official Ollama library build. For the exact Q4_K_M file from bartowski/SmolLM2-135M-Instruct-GGUF: ollama run hf.co/bartowski/SmolLM2-135M-Instruct-GGUF:Q4_K_M
Raise the context window
Type it inside the chat. For the API server instead, start it with OLLAMA_CONTEXT_LENGTH=8192 ollama serve.
$/set parameter num_ctx 8192
A larger context needs more memory than the weights alone.
Use the API
Ollama serves its API on http://localhost:11434.

Works on macOS, Windows and Linux.

Install LM Studio
Desktop app for macOS (Apple silicon), Windows and Linux.
lmstudio.ai ↗
Download the model
In the app press Ctrl/Cmd + Shift + M and paste https://huggingface.co/bartowski/SmolLM2-135M-Instruct-GGUF, then pick Q4_K_M. Or use the CLI (run LM Studio once first):
$lms get https://huggingface.co/bartowski/SmolLM2-135M-Instruct-GGUF@Q4_K_M
Open on Hugging Face ↗
Load and chat
Open the model loader, select the model and set Context Length to 8192. Leave GPU offload at maximum if it fits.
Start the local server (optional)
$lms server start

Works on macOS, Windows and Linux.

Install llama.cpp (macOS)
MacPorts, Nix and conda-forge also work.
$brew install llama.cpp
Install options ↗
Install llama.cpp (Windows)
$winget install llama.cpp
Install llama.cpp (Linux)
Download the prebuilt llama-*-bin-ubuntu-* archive for your GPU backend (CPU, Vulkan) from the releases page, unpack it and run the binaries from that folder. Homebrew (brew install llama.cpp) and conda-forge also work on Linux.
llama.cpp releases ↗
Start the server
Downloads the model on first run. The chat UI and an OpenAI-compatible API are at http://localhost:8080.
$llama-server -hf bartowski/SmolLM2-135M-Instruct-GGUF:Q4_K_M -c 8192 -ngl 99 --port 8080

Works on macOS, Windows and Linux.

Option A: Docker Model Runner
Docker Desktop: Settings > AI > Enable Docker Model Runner. Docker Engine on Linux: install the docker-model-plugin package.
$docker model run hf.co/bartowski/SmolLM2-135M-Instruct-GGUF:Q4_K_M
Model Runner docs ↗
The quant tag after the repo is how Hugging Face cards write it; if your Docker version rejects it, drop the tag and pick the quant by repo.
Option B: llama.cpp server image (NVIDIA)
Needs the NVIDIA Container Toolkit. Models are cached in the llama-cache volume. Open http://localhost:8080.
$docker run --gpus all -p 8080:8080 -v llama-cache:/root/.cache ghcr.io/ggml-org/llama.cpp:server-cuda -hf bartowski/SmolLM2-135M-Instruct-GGUF:Q4_K_M -c 8192 -ngl 99 --host 0.0.0.0 --port 8080
Image tags (cuda13, vulkan, rocm) ↗
Cache path inside the image is not in the docs; remove the -v flag if the volume complains.

Linux only.

Install vLLM
Linux only; on Windows run it inside WSL2. NVIDIA GPU shown; AMD ROCm, Intel and CPU builds have their own install pages.
$uv venv --python 3.12 --seed
$source .venv/bin/activate
$uv pip install vllm --torch-backend=auto
vLLM installation ↗
Serve the model
OpenAI-compatible API at http://localhost:8000/v1.
$vllm serve HuggingFaceTB/SmolLM2-135M-Instruct --max-model-len 8192
Runs the original weights, not the Q4_K_M GGUF; needs ~0 GB of GPU memory.

macOS only.

MLX supports only macOS, so follow these steps for that setup.

Install mlx-lm
$pip install mlx-lm
Chat in the terminal
$mlx_lm.chat --model HuggingFaceTB/SmolLM2-135M-Instruct-Q8-mlx
Downloads the model on first run. The MLX repo has its own quantisation; it may not match the quant selected above.
Or start a local server
Listens on http://localhost:8080.
$mlx_lm.server --model HuggingFaceTB/SmolLM2-135M-Instruct-Q8-mlx

Works on macOS, Windows and Linux.

Install Jan
jan.ai ↗
Find the model
Open the Hub tab, paste this model ID in Search, and choose Q4_K_M if offered.
$bartowski/SmolLM2-135M-Instruct-GGUF
Use the local API (optional)
Settings > Local API Server > Start Server. It listens on http://127.0.0.1:1337.

Rent GPUs hourly to run Q4_K_M right there. Pricing comes from partner marketplaces and varies.

Available GPU rentals for Q4_K_M, prioritized by value
GPU	Speed	$/1M tokens	Rent
RTX 3080 Ti (12 GB)CheapestCheapest11 GB free	~1379 tok/s	$0.025	Deploy on Vast.aifrom $0.12/hr (opens in new tab)	12 GB · 11 GB free · ~1379 tok/s · $0.025 / 1M tokens
RTX 3060 12GB11 GB free	~544 tok/s	$0.031	Deploy on Vast.aifrom $0.061/hr (opens in new tab)	11 GB free · ~544 tok/s · $0.031 / 1M tokens
RTX 4060 (8 GB)7 GB free	~411 tok/s	$0.058	Deploy on Vast.aifrom $0.086/hr (opens in new tab)	8 GB · 7 GB free · ~411 tok/s · $0.058 / 1M tokens
RTX A4000 (16 GB)15 GB free	~677 tok/s	$0.036	Deploy on Vast.aifrom $0.088/hr (opens in new tab)	16 GB · 15 GB free · ~677 tok/s · $0.036 / 1M tokens
RTX 4070 SUPER (12 GB)11 GB free	~762 tok/s	$0.038	Deploy on Vast.aifrom $0.10/hr (opens in new tab)	12 GB · 11 GB free · ~762 tok/s · $0.038 / 1M tokens
RTX PRO 4500 (32 GB)31 GB free	~1354 tok/s	$0.070	Deploy on RunPodfrom $0.34/hr (opens in new tab)	32 GB · 31 GB free · ~1354 tok/s · $0.070 / 1M tokens
RTX 4090 (24 GB)23 GB free	~1524 tok/s	$0.062	Deploy on RunPodfrom $0.34/hr (opens in new tab)	24 GB · 23 GB free · ~1524 tok/s · $0.062 / 1M tokens
A40 (48 GB)47 GB free	~1052 tok/s	$0.092	Deploy on RunPodfrom $0.35/hr (opens in new tab)	48 GB · 47 GB free · ~1052 tok/s · $0.092 / 1M tokens
L4 (24 GB)23 GB free	~454 tok/s	$0.27	Deploy on RunPodfrom $0.44/hr (opens in new tab)	24 GB · 23 GB free · ~454 tok/s · $0.27 / 1M tokens

Compare GPUs →

Your own private copy of SmolLM2 135M Instruct · Q4_K_M · OpenAI-compatible API

Open the llama.cpp listing on RunPod
Open on RunPodServerless (opens in new tab)
New to RunPod? Sign up and add credit first.
2
Fill in the form
Press Deploy and fill in:
Model
bartowski/SmolLM2-135M-Instruct-GGUF
Quantization
Q4_K_M
Context Size
16384
After pasting the model press Esc — don’t pick a suggestion. Press Next.
Create the endpoint
Keep the default 24 GB and 48 GB, then Create Endpoint. Right away: Manage → Edit endpoint → Max workers 1 → Save (changing settings later restarts the worker).
The first start downloads the model, usually 5–15 min. After that, replies after a pause come in seconds.
Create an API key
RunPod → Settings → API Keys → Create. Pick “Restricted” with access to this endpoint only.

Use it

Copy the endpoint URL from its page on RunPod (any of its links works) and paste it with the key. Both stay in this browser.

Endpoint URL

API key

Chats and keys stay only in this browser.

https://api.runpod.ai/v2/<ENDPOINT_ID>/openai/v1

Put your endpoint ID in place of <ENDPOINT_ID>. The API key is the one from step 2.

from openai import OpenAI
client = OpenAI(base_url="https://api.runpod.ai/v2/<ENDPOINT_ID>/openai/v1", api_key="rpa_...")
r = client.chat.completions.create(
    model="any",
    messages=[{"role": "user", "content": "Hello!"}])
print(r.choices[0].message.content)

Works with any OpenAI client.

https://api.runpod.ai/v2/<ENDPOINT_ID>/openai/v1

Put your endpoint ID in place of <ENDPOINT_ID>. The API key is the one from step 2.

Free on Windows, macOS, Linux, iOS, Android and the web.

Open the web app ↗ (opens in a new tab)Download ↗ (opens in a new tab)

1. Settings → Model Provider → Add → Add Custom Provider
2. API Mode OpenAI API Compatible; paste the API key and the base URL as API Host
3. Model → Fetch, pick the model
4. New chat → pick the provider → start chatting

Free and open source for Windows, macOS and Linux.

Download Jan ↗ (opens in a new tab)

1.Settings → next to Model Providers press +
2.API format OpenAI-compatible; Base URL is the base URL above (with /v1); API key is your key; Create
3.If no model appears, click + in Models and type any
4.New chat → pick the model → start chatting

How Much VRAM Does SmolLM2 135M Instruct Need?

Select a quantization level; the listed hardware adheres to it.

VRAM	+32K	+128K	File	Quality	On RTX 4090 (reference)
0.4 GB	—	—	~0 GB	2-bit · i-quant extreme compression — Importance-weighted 2-bit, extreme compression — significant quality loss	Fits: 8K context · ~1724 tok/s
0.4 GB	—	—	~0 GB	2-bit · i-quant extra small — Importance-weighted 2-bit, extra small	Fits: 8K context · ~1680 tok/s
0.4 GB	—	—	~0.1 GB	2-bit · i-quant medium — Importance-weighted 2-bit, medium	Fits: 8K context · ~1680 tok/s
0.4 GB	—	—	~0 GB	2-bit · i-quant small — Importance-weighted 2-bit, small	Fits: 8K context · ~1680 tok/s
0.4 GB	—	—	0.1 GB	3-bit · i-quant extra small — Importance-weighted 3-bit, extra small	Fits: 8K context · ~1638 tok/s
0.4 GB	—	—	0.1 GB	3-bit · i-quant small — Importance-weighted 3-bit, small	Fits: 8K context · ~1638 tok/s
0.4 GB	—	—	0.1 GB	2-bit · K-quant — 2-bit quantization with K-quant improvements	Fits: 8K context · ~1638 tok/s
0.4 GB	—	—	~0.1 GB	3-bit · i-quant — Importance-weighted 3-bit	Fits: 8K context · ~1638 tok/s
0.4 GB	—	—	0.1 GB	3-bit small — 3-bit small quantization	Fits: 8K context · ~1598 tok/s
0.4 GB	—	—	0.1 GB	4-bit · legacy — 4-bit legacy quantization	Fits: 8K context · ~1598 tok/s
0.4 GB	—	—	0.1 GB	3-bit medium — 3-bit medium quantization	Fits: 8K context · ~1598 tok/s
0.4 GB	—	—	~0.1 GB	3-bit · i-quant medium — Importance-weighted 3-bit, medium	Fits: 8K context · ~1598 tok/s
0.4 GB	—	—	0.1 GB	3-bit large — 3-bit large quantization	Fits: 8K context · ~1560 tok/s
0.4 GB	—	—	0.1 GB	4-bit small — 4-bit small quantization	Fits: 8K context · ~1560 tok/s
0.4 GB	—	—	0.1 GB	4-bit · i-quant compact — Importance-weighted 4-bit, compact	Fits: 8K context · ~1560 tok/s
0.4 GB	—	—	0.1 GB	4-bit large — 4-bit large quantization	Fits: 8K context · ~1524 tok/s
0.4 GB	—	—	0.1 GB	4-bit medium — 4-bit medium quantization — most popular sweet spot	Fits: 8K context · ~1524 tok/s
0.4 GB	—	—	0.1 GB	5-bit large — 5-bit large quantization	Fits: 8K context · ~1489 tok/s
0.4 GB	—	—	0.1 GB	5-bit small — 5-bit small quantization	Fits: 8K context · ~1489 tok/s
0.4 GB	—	—	0.1 GB	5-bit medium — 5-bit medium quantization — good quality/size tradeoff	Fits: 8K context · ~1489 tok/s
0.5 GB	—	—	0.1 GB	6-bit, very good — 6-bit quantization, very good quality	Fits: 8K context · ~1424 tok/s
0.5 GB	—	—	0.1 GB	8-bit, near-lossless — 8-bit quantization, near-lossless	Fits: 8K context · ~1365 tok/s
0.6 GB	—	—	0.3 GB	16-bit · bfloat — Brain floating point 16 — preferred for training	Fits: 8K context · ~1057 tok/s

Selected Q4_K_M

4-bit medium quantization

0.6GBat 8K context

Weights: 0.1 GB
KV cache: 0.2 GB
Overhead: 0.3 GB

Fits RTX 4090 (reference) · 23.4 GB free · ~1524 tok/s

≥50 tok/s needs ≥33 GB/s · RTX 5090 ~2709, RTX 3090 Ti ~1524

Which Hardware Can Run SmolLM2 135M Instruct?

Q4_K_M · 0.4 GB

SmolLM2 135M Instruct (Q4_K_M) requires 0.4 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 0.1 GB, bringing total usage to 0.6 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run SmolLM2 135M Instruct, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M

Typical hardwareQuantVRAMtok/sContext that fits

8 GB · RTX 4060Q4_K_M · 0.6 GB · ~411 tok/s · 8K0.6~4118K8 GB tier →

12 GB · RTX 3060 12GBQ4_K_M · 0.6 GB · ~544 tok/s · 8K0.6~5448K12 GB tier →

16 GB · RTX 5060 Ti 16GBQ4_K_M · 0.6 GB · ~677 tok/s · 8K0.6~6778K16 GB tier →

24 GB · RTX 4090referenceQ4_K_M · 0.6 GB · ~1524 tok/s · 8K0.6~15248K24 GB tier →

Mac 32 GB · Mac Mini M4Q4_K_M · 0.6 GB · ~195 tok/s · 8K0.6~1958KMacs →

Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 0.6 GB · ~889 tok/s · 8K0.6~8898KMacs →

Alternatives to SmolLM2 135M Instruct

SmolLM family · 15 models →

Similar models

4tok/s on RTX 4090

Model	Score	VRAM	tok/s	Why it is similar
Mamba 130M HFState Spaces	—	0.9 GB	~7280	same size
Opt 125MMeta	—	0.3 GB	~2340	same size
Gpt2OpenAI	—	0.1 GB	~7280	same size
Gpt2 Small DutchGroNLP	—	0.1 GB	~7280	same size

Fine-tunes & variants(3)community builds of SmolLM2 135M Instruct

Specifications

Publisher: Hugging Face
Family: SmolLM
Parameters: 135M
Architecture: LlamaForCausalLM
Context Length: 8,192 tokens
Vocabulary Size: 49,152
Release Date: 2024-10-31
License: Apache 2.0

Resources

Frequently Asked Questions

How much VRAM does SmolLM2 135M Instruct need?

SmolLM2 135M Instruct requires 0.4 GB of VRAM at Q4_K_M, or 0.6 GB at BF16.

VRAM = Weights + KV Cache + Overhead

Weights = 135M × 4.8 bits ÷ 8 = 0.1 GB

KV Cache + Overhead ≈ 0.3 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 ≈ 0.5 GB (at full 8K context)

VRAM usage by quantization

Q4_K_M

0.4 GB

Q4_K_M + full context

0.6 GB

Learn more about VRAM estimation →

What's the best quantization for SmolLM2 135M Instruct?

For SmolLM2 135M Instruct, Q4_K_M (0.4 GB) offers the best balance of quality and VRAM usage. Q4_K_L (0.4 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 0.4 GB.

VRAM requirement by quantization

IQ2_XXS

0.4 GB~53%

Q2_K

0.4 GB~75%

IQ3_M

0.4 GB~78%

Q4_K_M ★

0.4 GB~89%

Q5_K_L

0.4 GB~92%

BF16

0.6 GB~100%

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run SmolLM2 135M Instruct on a Mac?

Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run SmolLM2 135M Instruct. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.4 GB of usable unified memory (RAM minus macOS overhead).

Can I run SmolLM2 135M Instruct locally?

Yes — SmolLM2 135M Instruct can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is SmolLM2 135M Instruct?

At Q4_K_M, SmolLM2 135M Instruct can reach ~11163 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1524 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 ÷ 0.43 × 0.65 = ~12093 tok/s

Estimated speed at Q4_K_M (0.4 GB)

NVIDIA B200

~12093 tok/s

NVIDIA GeForce RTX 4090

~1524 tok/s

NVIDIA B300

~12093 tok/s

AMD Instinct MI350X

~11163 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of SmolLM2 135M Instruct?

At Q4_K_M, the download is about 0.08 GB. The full-precision BF16 version is 0.27 GB. The smallest option (IQ2_XXS) is 0.04 GB.

Which GPUs can run SmolLM2 135M Instruct?

52 consumer GPUs can run SmolLM2 135M Instruct 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 135M Instruct?

163 devices with unified memory can run SmolLM2 135M Instruct at Q4_K_M (0.4 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.