v2.2 · 2026-06-12

OLMo 2 1124 7B Instruct

olmo-2-1124-7b-instruct

TEXT-CHAT

OLMo 2 1124 7B Instruct is a 7B text chat model profile for local AI planning. This page records provider, license, context, quantization, hardware-fit estimates, setup hints, source links, and caveats so readers do not choose a model by name alone.

PROVIDER

Ai2 / Allen Institute for AI

FAMILY

OLMo 2

MODEL TYPE

text-chat

PARAMETERS

MODALITIES

text

ARCHITECTURE

OLMo 2 decoder-only transformer, post-trained with Tülu 3 supervised fine-tuning, DPO and reinforcement learning with verifiable rewards.

CONTEXT WINDOW

4,096 tokens

TRAINING TOKENS

—

RELEASE DATE

2024-11-26

LICENSE & LINKS

Apache-2.0license text

MODEL CARD

huggingface.co/allenai/OLMo-2-1124-7B-Instruct

HUGGING FACE

allenai/OLMo-2-1124-7B-Instruct

GGUF REPOSITORIES

allenai/OLMo-2-1124-7B-Instruct-GGUF official

Official Ai2 GGUF repository with Q4_K_M, Q5_K_M and Q8_0 file listings.

SETUP HINTS

OLLAMA

Run `ollama run olmo2:7b` or a specific quantized tag such as `olmo2:7b-q4_K_M`.

LM STUDIO

Use the official `allenai/OLMo-2-1124-7B-Instruct-GGUF` repository and select Q4_K_M or Q5_K_M.

LLAMA.CPP

Use a standard text GGUF loader against the official Ai2 GGUF repository.

QUANTIZATION FILE SIZES (GGUF)

Q4_K_M

4.47 GB

Q5_K_M

5.21 GB

Q8_0

7.76 GB

Quantization note: Q4_K_M for general local chat; Q5_K_M if you can spare modest extra RAM.

RAM / VRAM ESTIMATES

MIN RAM

8 GB

COMFORTABLE RAM

16 GB

MIN VRAM

6 GB

COMFORTABLE VRAM

8 GB

These are conservative local-inference estimates, not official hardware requirements.

HARDWARE FIT

CPU only (no GPU)

limited

8 GB RAM

limited

16 GB RAM

yes

32 GB RAM

yes

8 GB VRAM

yes

12 GB VRAM

yes

24 GB VRAM

yes

Apple Silicon (unified memory)

yes

Hardware fit values are conservative local-inference estimates based on GGUF size plus runtime and KV-cache overhead. Actual requirements depend on context length, quantization, runtime, GPU offload, and other running apps.

BEST FOR

·Fully open local assistant experiments

·Research and education

·General chat

·Summarization and classification

·Open-science model comparison

AVOID IF

·You need a verified structured tool-calling model

·You need multilingual support beyond primarily English

·You need vision

·You only have very constrained 8GB RAM and want smooth performance

CAVEATS

·Ollama and release sources describe the OLMo 2 family as trained up to 5T tokens, but the exact instruct checkpoint token count was not separately verified, so `trainingTokens` is null.

·The official model card describes the language as primarily English.

·The model card does not verify structured tool-calling support, so `supportsTools` is null.

·RAM and VRAM estimates are derived from GGUF/Ollama package size plus conservative overhead; KV cache, context length, batch size, runtime and GPU offload choices can materially change memory needs.

SOURCE URLS