whatmodel.sh / Nemotron-Cascade-14B-Thinking

Nemotron-Cascade-14B-Thinking

+ contribute

Nemotron-Cascade-14B-Thinking is an open-weights language model from NVIDIA, released December 2025. Its published size is 14.77B parameters. Licence: nvidia-open-model-license.

Catalogue identity notes

NVIDIA's own model, repo nvidia/Nemotron-Cascade-14B-Thinking @8aa18a0 (licence nvidia-open-model-license). 'post-trained from the Qwen3-14B Base model', thinking mode only. Printed as 'Nemotron-Cascade-14B-Thinking' in the Nemotron-Cascade report (arXiv 2512.13607v2) Table 9; listed so the report's NVIDIA rows join the existing LiveCodeBench Pro 25Q2 runs.

Model information sources

Release date ↗ · Weights licence ↗

safetensors metadata of nvidia/Nemotron-Cascade-14B-Thinking @8aa18a0: 14,768,307,200 parameters (dense).

60.5±1.0#189 of 719 LLMsfrom 12 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of Nemotron-Cascade-14B-Thinking, out of 828 with a score, then more from NVIDIA.

#	model	score	where	RAM	released
225	Qwen3 30B-A3B Thinking 2507 Alibaba	61±1	api $0.75/M +local	~20GB	2025-07
226	Qwen3.5 4B Alibaba	61±1	local	~4.3GB	2026-03
227	Nemotron-Cascade-14B-Thinking NVIDIA	61±1	local	~10GB	2025-12
228	Mellum2.1 12B-A2.5B Thinking JetBrains	60±2	local	~8.3GB	2026-09
229	GPT-4.1 mini OpenAI	60±1	api $0.70/M		2025-04
	more from NVIDIA
98	Nemotron 3 Ultra 550B-A55B NVIDIA	69±1	api $1.35/M +local	~89GB	2026-06
155	Nemotron Cascade 2 30B-A3B NVIDIA	66±1	local	~20GB	2026-03
168	Nemotron 3 Super 120B-A12B NVIDIA	65±1	api $0.28/M +local	~73GB	2026-03

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #169 of 300 * · 7.3% of its score · 2 tests

Beats o1 (2024-12-17), o3-mini, DeepSeek R1 0528 here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Mini, Jamba 1.5 Large here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
SWE-bench Verified lab	43.1% ✎	▁▁▁▁▁▁▂▄█▆▁▁ beats 32/131	hard · avg 19%	▇▇ 6.0%	sharp · at its level · small run
BFCL v3 lab	67.5% ✎	▁▁▁▁▁▃▅█▆▅▄▁ beats 135/170	medium · avg 58%	▇ 1.4%	blunt · at its level · small run

coding▁▁▁▃▆██▇▆▄▃▁ #165 of 458 · 56% of its score · 4 tests

Beats Qwen3-Coder-Next (80B-A3B), Qwen3-VL 235B-A22B Instruct, Qwen3-Next 80B-A3B Instruct here, though they rank higher overall. Trails QwQ-32B-Preview, Ministral 3 8B Reasoning 2512, Phi-4-reasoning 14B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
LiveCodeBench Pro 2025Q2 (Medium) lab	10.5% ✎	▃▃····▃·█·▃▃ beats 7/7	very hard · avg 2.4%	▇▇▇▇▇▇▇▇▇▇▇▇▇ 33%	sharp
LiveCodeBench Pro 2025Q2 (Easy) lab	68.9% ✎	▄·▄····▄▄▄█▄ beats 7/7	medium · avg 45%	▇▇▇▇▇ 12%	at its level
SWE-bench Verified lab	43.1% ✎	▁▁▁▁▁▁▂▄█▆▁▁ beats 32/131	hard · avg 19%	▇▇ 6.0%	sharp · at its level · small run
LiveCodeBench v6 (Aug 2024–May 2025) lab	74.6% ✎	▄▄···▄·▄▄█·▄ beats 7/7	medium · avg 57%	▇▇ 5.5%	at its level

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #187 of 393 * · 1.7% of its score · 1 test

Beats Seed-OSS 36B Instruct here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, LFM2.5 1.2B Thinking, Gemma 3 12B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
IFEval prompt-level strict lab	81.9% ✎	▁▁··▂··▂▇█▃▃ beats 12/26	easy · avg 77%	▇ 1.7%	small run

math▁▂▃▅▆▅▄█▄▁▁▁ #121 of 398 * · 16% of its score · 2 tests

Beats Claude Sonnet 4.6, MiniMax-M3, MiMo-V2.5 (310B-A15B) here, though they rank higher overall. Trails Olmo 3.1 32B Think here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
AIME 2025 lab	83.3% ✎	▁·▁▁▁▂▅▆█▇▅▁ beats 93/133	medium · avg 55%	▇▇▇ 8.6%	sharp · small run
AIME 2024 lab	89.7% ✎	▁▁▁▂▁▃▁▅███▃ beats 71/85	easy · avg 68%	▇▇▇ 7.8%	sharp · small run

other tests4 not in a task · 24% of its score

test	result	vs the others in its run	difficulty	counts	why
GPQA Diamond lab	69.6% ✎	▁▁▁▁▂▄▅▅███▄ beats 152/310	hard · avg 46%	▇▇▇▇ 10%	sharp · at its level · small run
MMLU lab	85.1% ✎	▁▁▁▁▁▂▃▅█▃▆▃ beats 156/183	medium · avg 73%	▇▇ 5.4%	small run
MMLU-Pro lab	77.0% ✎	▁▁·▁▁▁▃▂▄▅█▁ beats 108/188	medium · avg 60%	▇▇ 4.7%	small run
IFBench (aggregation unspecified) lab	41.7% ✎	▃▇▂▄▅▅▂▄▄▆█▇ beats 29/80	hard · avg 31%	▇ 3.4%	at its level · small run

$ where to run it

llama.cpp · recommended

version

Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
macOS / Linux
curl -LsSf https://llama.app/install.sh | sh
Windows
irm https://llama.app/install.ps1 | iex
other ways to install ↗
Run Nemotron-Cascade-14B-Thinking · needs ~9 GB · from huggingface.co/bartowski
chat in the terminal
llama cli -hf bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF:Q4_K_M

LM Studio

version

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run Nemotron-Cascade-14B-Thinking · needs ~9 GB · from huggingface.co/bartowski
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF@Q4_K_M -y
Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

Install Ollama
download it (macOS / Windows) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run Nemotron-Cascade-14B-Thinking · needs ~9 GB · from huggingface.co/bartowski
chat in the terminal
ollama run hf.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF:Q4_K_M

MLX (Mac)

Install MLX (Mac) · Apple silicon Macs only, text only.
with uv
uv tool install mlx-lm
or
pip install mlx-lm
Run Nemotron-Cascade-14B-Thinking · needs ~8.3 GB, Mac only · from huggingface.co/introvoyz041
chat in the terminal
mlx_lm.chat --model introvoyz041/Nemotron-Cascade-14B-Thinking-mlx-4Bit
Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model introvoyz041/Nemotron-Cascade-14B-Thinking-mlx-4Bit

Official weights and documentation: huggingface.co/nvidia ↗

$ how the score was worked out · NVIDIA — Nemotron-Cascade: Sc… 100%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
NVIDIA — Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models · lab-reported	12	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 100%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 60.5

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated 2026-10-11 02:20 UTC · sources and licences · json