FitMyLLM
Shanghai AI Lab/Dense

Shanghai AI LabInternLM3 8B Instruct

InternLM3 8B Instruct from Shanghai AI Lab: dense, 8.8B parameters, 32K context. Tagged for coding, reasoning, multilingual, math.

chatcodingreasoningmultilingualmath
8.8B
Parameters
32K
Context length
11
Benchmarks
6
Quantizations
0
Architecture
Dense
Released
2026-01-15
Layers
48
KV Heads
2
Head Dim
128
Family
internlm

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
6.4 GB
5.9 + 0.6 KV
good
Q5_K_S5.57
7.2 GB
6.6 + 0.6 KV
good
Q5_K_M5.7
7.3 GB
6.8 + 0.6 KV
good
Q6_K6.56
8.3 GB
7.7 + 0.6 KV
excellent
Q8_08.5
10.4 GB
9.8 + 0.6 KV
lossless
FP1616
18.7 GB
18.1 + 0.6 KV
lossless

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

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run InternLM3 8B Instruct now

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (11)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$# InternLM3 8B Instruct is not in Ollama's library, and we know no GGUF build of it

Search Hugging Face for a GGUF of it (https://huggingface.co/models?sort=trending&search=internlm3-8b-instruct+GGUF), or use the vLLM tab with the original weights.

Setup guide
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Tesla C2070
6 GB VRAM • 143 GB/s
NVIDIA
NVIDIA Tesla C2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla C2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla M2070
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2070-Q
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2070
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla K20X
6 GB VRAM • 250 GB/s
NVIDIA
NVIDIA Tesla K20Xm
6 GB VRAM • 250 GB/s
NVIDIA

Find the best GPU for InternLM3 8B Instruct

Build Hardware for InternLM3 8B Instruct
Spec sheet

InternLM3 8B Instruct — 8.8B Dense.

Specifications
Parameters
8.8B
Architecture
Dense Transformer
Context Length
32K tokens
Capabilities
chat, coding, reasoning, multilingual, math
Release Date
2026-01-15
Provider
Shanghai AI Lab
Family
internlm
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.895.9 GB94%
Q5_K_S5.576.6 GB96%
Q5_K_M5.76.8 GB96%
Q6_K6.567.7 GB97%
Q8_08.59.8 GB100%
FP161618.1 GB100%
Benchmark scores
HumanEval82.3
MMLU-PRO57.6
MATH25.3
IFEval55.4
BBH57.0
GPQA13.0
MUSR16.3
BigCodeBench25.8
GPQA Diamond37.4
LiveCodeBench17.8
MATH-50083.0
Compatible GPUs
30 @ Q4_K_M