llmrun
OpenGVLabInternVLChatModel

InternVL3 5 8B — Hardware Requirements & GPU Compatibility

Vision

InternVL3.5-8B is OpenGVLab's 8.5-billion-parameter multimodal model, which pairs a 0.3-billion-parameter vision encoder with an 8.2-billion-parameter language model. The card notes that the InternVL3.5 family uses Cascade Reinforcement Learning, applying offline RL before online RL to boost reasoning and versatility across multimodal, text, and agentic tasks; this checkpoint is a finetune of InternVL3_5-8B-MPO. It works well for image and document question answering, reasoning over visual content, and agent-style tasks. At this size it can run on a single consumer GPU once quantized. The card doesn't state a context length, so none is provided here. Released under the Apache 2.0 license, it allows both commercial and research use. Published in August 2025, it falls in the middle of the InternVL3.5 lineup, which includes dense models ranging from 1B to 38B parameters plus larger mixture-of-experts variants reaching up to 241B total parameters.

8.5B params · denseApache 2.0103.8K downloads109 likes11.9K quant downloads
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 8KBest on24 GB Q4_K_M · ~116 tok/s · 32KMacs from16 GB Q4_K_M · ~25 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run InternVL3 5 8B

One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.

Recommended

Ollama
one command · needs Ollama installed
$ollama run hf.co/bartowski/OpenGVLab_InternVL3_5-8B-GGUF:Q4_K_M

Q4_K_M fits fully on the RTX 4090 · 15.8 GB free · 16K context

Download: OpenGVLab_InternVL3_5-8B-Q4_K_M.gguf5.03 GBbartowski

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Your own private copy · Q4_K_M · 24 GB GPU

  • The easiest way to try this model
  • Running in a few minutes, easy setup
  • Chat right here or connect any app

$5+ bonus for new users

How Much VRAM Does InternVL3 5 8B Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
4.0 GB9.6 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 32K context · ~164 tok/s
4.1 GB9.7 GB3-bit small — 3-bit small quantizationFits: 32K context · ~160 tok/s
4.6 GB10.2 GB3-bit medium — 3-bit medium quantizationFits: 32K context · ~143 tok/s
4.7 GB10.3 GB4-bit · legacy — 4-bit legacy quantizationFits: 32K context · ~140 tok/s
5.6 GB11.2 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 32K context · ~116 tok/s
6.7 GB12.3 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 32K context · ~98 tok/s
7.7 GB13.3 GB6-bit, very good — 6-bit quantization, very good qualityFits: 32K context · ~85 tok/s
9.4 GB15 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 32K context · ~70 tok/s

Selected Q4_K_M

4-bit medium quantization

8.2GBat 16K context

Weights
5.0 GB
KV cache
3.0 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 15.8 GB free · ~116 tok/s

≥50 tok/s needs ≥433 GB/s · RTX 5090 ~207, M5 Ultra ~153

Which Hardware Can Run InternVL3 5 8B?

Q4_K_M · 5.6 GB

InternVL3 5 8B (Q4_K_M) requires 5.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. 107 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 172 devices with unified memory can run InternVL3 5 8B, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB), NVIDIA Jetson Orin Nano 8GB (Super).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Q4_K_M · 8.2 GB · ~31 tok/s · 8Ktight8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 8.2 GB · ~42 tok/s · 32K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 8.2 GB · ~52 tok/s · 32K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 8.2 GB · ~116 tok/s · 32K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 8.2 GB · ~15 tok/s · 32KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 8.2 GB · ~68 tok/s · 32KMacs →

Alternatives to InternVL3 5 8B

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
Granite Switch 4.1 8BIBM—8.4 GB~111same size
Apertus V1.5 8Bswiss-ai—8.5 GB~111same size
LFM2.5 8B A1BLiquid AI—5.6 GB~335same size
BitCPM CANN 8BOpenBMB—5.6 GB~127same size
Gemma 4 E4BGoogle—5.6 GB~123same size
Qwen3 VL 8B InstructAlibaba—8 GB~112same size

Specifications

Publisher
OpenGVLab
Parameters
8.5B
Architecture
InternVLChatModel
Release Date
2025-08-25
License
Apache 2.0

Frequently Asked Questions

How much VRAM does InternVL3 5 8B need?

InternVL3 5 8B requires 5.6 GB of VRAM at Q4_K_M, or 18.8 GB at BF16.

VRAM = Weights + KV Cache + Overhead

Weights = 8.5B × 4.8 bits ÷ 8 = 5.1 GB

KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

VRAM usage by quantization

5.6 GB

Learn more about VRAM estimation →

What's the best quantization for InternVL3 5 8B?

For InternVL3 5 8B, Q4_K_M (5.6 GB) offers the best balance of quality and VRAM usage. Q4_K_L (5.8 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 2.6 GB.

VRAM requirement by quantization

IQ2_XXS
2.6 GB
IQ3_XS
3.9 GB
Q3_K_L
4.8 GB
Q4_K_M ★
5.6 GB
Q4_K_L
5.8 GB
BF16
18.8 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run InternVL3 5 8B on a Mac?

Yes — Mac Mini M2 Pro (16 GB) and 145 other Macs can run InternVL3 5 8B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.6 GB of usable unified memory (RAM minus macOS overhead).

Can I run InternVL3 5 8B locally?

Yes — InternVL3 5 8B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is InternVL3 5 8B?

At Q4_K_M, InternVL3 5 8B can reach ~853 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~116 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = (bandwidth GB/s ÷ model GB) × efficiency

Example: NVIDIA B200 → 8000 ÷ 5.63 × 0.65 = ~924 tok/s

Estimated speed at Q4_K_M (5.6 GB)

~924 tok/s
~116 tok/s
~924 tok/s
~853 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of InternVL3 5 8B?

At Q4_K_M, the download is about 5.12 GB. The full-precision BF16 version is 17.06 GB. The smallest option (IQ2_XXS) is 2.35 GB.

Which GPUs can run InternVL3 5 8B?

107 consumer GPUs can run InternVL3 5 8B at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6700M, AMD Radeon RX 6750 XT, AMD Radeon RX 5600 XT. 51 GPUs have plenty of headroom for comfortable inference.

Which devices can run InternVL3 5 8B?

172 devices with unified memory can run InternVL3 5 8B at Q4_K_M (5.6 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.