LocalClaw/LLM/NVIDIA Dory 1.0 4B
Open-weight local LLM

NVIDIA Dory 1.0 4B

Use case: Coding assistant. Check the memory fit and choose a setup path below.

16 GB catalogue minimum16 GB RAMQ5_K_MCoding assistant
Choose an app

This model needs a special runtime. Unsupported apps are clearly marked.

Compare models
LM StudioNot available for this model
UnslothNot available for this model
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloads
llama.cppNot available for this model
Use with LocalClawOptional workspace after the model is installed
This model needs its official runtimeDory-enabled llama.cpp at 98a74c97ea09ac72f6ceda1559808fc0a2f447ce (Apple Silicon reference setup)
Parameters
4B
Minimum RAM
16 GB
Model size
3.67 GB
Quantization
Q5_K_M

About NVIDIA Dory 1.0 4B

Catalogue summary: NVIDIA OpenMDW-1.1 open-weight reasoning model with recurrent layers and official 3.67GB Q5_K_M GGUF. The documented Apple Silicon setup uses a pinned Dory-enabled llama.cpp build and 4096-token context. Budget 16GB unified memory; the 256K model limit is not a 16GB memory guarantee.

NVIDIA Dory 1.0 4B has a catalogue minimum of 16 GB RAM with Q5_K_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use the official Dory-enabled llama.cpp at 98a74c97ea09ac72f6ceda1559808fc0a2f447ce (Apple Silicon reference setup) setup. The current low-bit files are not a stock LM Studio install.

Model sourcePublic GGUF repository (verified 2026-11-06): nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-GGUFUpstream releaseLicence text
chatcodereasoningtool-calling

Install path

01
Check RAM fitMinimum 16 GB RAM. Start with the Q5_K_M quant.
02
Load the modelFollow the official Dory-enabled llama.cpp at 98a74c97ea09ac72f6ceda1559808fc0a2f447ce (Apple Silicon reference setup) instructions. Stock LM Studio support is not confirmed.
03
Try your workloadStart with a short prompt, check memory use and adjust context length before running longer tasks.

Download formats for this model

These are quantizations of the same model. The RAM fit above uses Q5_K_M; larger files need more memory. File sizes exclude the runtime, context cache and optional vision projector.

Catalogue record

  • Family: nemotron
  • Parameters: 4B
  • Recommended quantization: Q5_K_M
  • Catalogue minimum RAM: 16 GB
  • Catalogue model size: 3.67 GB
  • Tags: chat, code, reasoning, tool-calling

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Reading the scores

LocalClaw /10 is an editorial catalogue rating. Community /5 comes from member reviews. Your machine fit is a separate memory and runtime assessment.

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
?
quality
?
coding
?
reasoning
?

Technical notes

Developer
NVIDIA
License
OpenMDW 1.1
Context window
262,144 tokens
Architecture
4B looped normalized-GPT with recurrent layers and interleaved sliding-window and full attention. Inference can reuse the recurrent block for different compute budgets.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Starter desktopMac mini M4 16GBPortable fitMacBook Air M4 16GBBest 16GB models16GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

Nemotron 3.5 Lightning 30B-A3B 30B (3B active, MoE)Nemotron Nano 9B v2 9BLlama-3.3-Nemotron-Super (49B) 49BApriel Nemotron 15B Thinker 15BLlama-3.1-Nemotron (70B) 70BNemotron Mini (4B) 4BSpark-X2.5-4B 4BAgents-A1 4B 4B

Where to go next