SmolLM2 135M Instruct on NVIDIA GeForce RTX 4070 SUPER

Can the NVIDIA GeForce RTX 4070 SUPER run SmolLM2 135M Instruct?

44 pts

Yes, it runs well

Runs well. At F16 it needs about 1.6 GB of 12.0 GB usable, with an estimated speed of 1,117 tok/s.

Best quant: F16
Generation speed: 1,117 tok/s
Prompt processing: 196,615 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 8K

Download SmolLM2 135M Instruct

Recommended for the NVIDIA GeForce RTX 4070 SUPER: F16. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run smollm2:135m-instruct-fp16

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the F16 file (opens in a new tab)

huggingface.co/unsloth/SmolLM2-135M-Instruct-GGUF (opens in a new tab)

ollama run hf.co/unsloth/SmolLM2-135M-Instruct-GGUF:F16

Original weights · Hugging Face

Full-precision files from Hugging Face, for fine-tuning, vLLM, Transformers.

huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Hugging Face. The weights themselves download from Hugging Face.

github.com/huggingface/smollm (opens in a new tab)

git clone https://github.com/huggingface/smollm

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How the C grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	1.8 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	3.2 / 15
Total	45.0 / 100	44 ptsUsable (C) · 44 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.2/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the NVIDIA GeForce RTX 4070 SUPER

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	1.4 GB	12.0 GB	7,816 tok/s	Runs well	44 ptsUsable (C) · 44 of 100 points: Model quality 1.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15	GGUF (opens in a new tab)
`Q3_K_M`	1.5 GB	12.0 GB	6,152 tok/s	Runs well	44 ptsUsable (C) · 44 of 100 points: Model quality 1.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15	GGUF (opens in a new tab)
`Q4_K_M`	1.5 GB	12.0 GB	4,759 tok/s	Runs well	44 ptsUsable (C) · 44 of 100 points: Model quality 1.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15	GGUF (opens in a new tab)
`Q5_K_M`	1.5 GB	12.0 GB	3,932 tok/s	Runs well	44 ptsUsable (C) · 44 of 100 points: Model quality 1.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15	GGUF (opens in a new tab)
`Q6_K`	1.5 GB	12.0 GB	3,302 tok/s	Runs well	44 ptsUsable (C) · 44 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.9/15	GGUF (opens in a new tab)
`Q8_0`	1.5 GB	12.0 GB	2,423 tok/s	Runs well	44 ptsUsable (C) · 44 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.9/15	GGUF (opens in a new tab)
`F16`	1.6 GB	12.0 GB	1,117 tok/s	Runs well	44 ptsUsable (C) · 44 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.2/15	GGUF (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

45 ptsUsable (C) · 45 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.2/15 NVIDIA GeForce RTX 4060 F16 · 603 tok/s
45 ptsUsable (C) · 45 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15 Apple M1 (16 GB) F16 · 130 tok/s
45 ptsUsable (C) · 45 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15 Apple M4 (16 GB) F16 · 229 tok/s
45 ptsUsable (C) · 45 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.4/15 Apple M4 (24 GB) F16 · 229 tok/s
45 ptsUsable (C) · 45 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.4/15 Apple M4 Pro (24 GB) F16 · 521 tok/s
44 ptsUsable (C) · 44 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.2/15 Intel Arc B580 F16 · 772 tok/s

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.