openthinker/Dense

OOpenThinker 7B

reasoningmath
7B
Parameters
31K
Context length
6
Benchmarks
6
Quantizations
Architecture
Dense
Released
2025-02-01
Layers
28
KV Heads
4
Head Dim
128
Family
openthinker

Quantization Options

QuantBitsVRAMQuality
Q4_K_M4.894.8 GBgood
Q5_K_S5.575.4 GBgood
Q5_K_M5.75.5 GBgood
Q6_K6.566.2 GBexcellent
Q8_08.57.9 GBlossless
FP161614.5 GBlossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Benchmarks (6)

MATH42.6
IFEval40.9
MMLU-PRO35.2
BBH34.5
MUSR5.4
GPQA0.9

Run this model

Easiest way to get starteddocs →
curl -fsSL https://ollama.com/install.sh | sh
$ollama run openthinker:7b:q4_k_m

Downloads and runs automatically. Add --verbose for speed stats.

Setup guide

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Find the best GPU for OpenThinker 7B

Build Hardware for OpenThinker 7B

OpenThinker 7B7B Parameter Dense LLM

Model Specifications

Parameters
7B
Architecture
Dense Transformer
Context Length
31K tokens
Capabilities
reasoning, math
Release Date
2025-02-01
Family
openthinker

VRAM Requirements

QuantizationBPWVRAMQuality
Q4_K_M4.894.8 GB94%
Q5_K_S5.575.4 GB96%
Q5_K_M5.75.5 GB96%
Q6_K6.566.2 GB97%
Q8_08.57.9 GB100%
FP161614.5 GB100%

Benchmark Scores

MMLU-PRO35.2
MATH42.6
IFEval40.9
BBH34.5
GPQA0.9
MUSR5.4

How to Run OpenThinker 7B

Run OpenThinker 7B locally with Ollama (needs 4.8 GB VRAM at Q4_K_M):

ollama run openthinker:7b

Compatible GPUs (30)

GPUs that can run OpenThinker 7B at Q4_K_M quantization: