VOOZH about

URL: https://willitrunai.com/gpus/quadro-rtx-6000-24gb

⇱ AI Models for Quadro RTX 6000 24GB β€” What Runs on 24GB VRAM


NVIDIA

Quadro RTX 6000 24GB

Quadro RTXWorkstationTuringPCIe 3CUDA

Operating mode

Choose the operating mode for this hardware

Use this to bias workload recommendations toward responsiveness, background autonomy, lighter serving, or multi-GPU scale-out.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

See Full AI Tier List for Quadro RTX 6000 24GB β†’

About this GPU for AI

The Quadro RTX 6000 is NVIDIA's Turing-generation flagship workstation GPU, featuring 24 GB of ECC GDDR6 with NVLink support. Released in 2018, it was the first Quadro card to support real-time ray tracing and dedicated Tensor Cores for AI acceleration. For current AI inference workloads, its Turing-generation INT4/INT8 Tensor Cores are still capable of running 7B–13B models reliably, though its 672 GB/s bandwidth and dated compute make it slower than consumer Ada or Ampere alternatives for token generation.

Beyond LLMs

AI Capability Matrix

What AI tasks this GPU can handle β€” from text generation to image and video creation.

CapabilityStatusRepresentative ModelDetail
LLM Chat (7B)Runs nativelyLlama 3.1 8B Q4β€”
LLM Coding (30B)Runs nativelyQwen 3 30B Q4β€”
LLM Large (70B)
workstation-gradeecc-memoryprofessional-certifiednvlink-capablelegacy

Specifications

Compute
FP1632 TFLOPS
INT8256 TOPS
ArchitectureTuring
Memory
VRAM24 GB
Bandwidth672 GB/s
General
FamilyQuadro RTX
SegmentWorkstation
InterconnectPCIe 3
Compute PlatformCUDA
MSRP$4,000

Key Features

24 GB ECC GDDR6 VRAMTuring architecture with 2nd-gen Tensor Cores (INT4, INT8, FP16)32 TFLOPS FP16672 GB/s memory bandwidthNVLink support for 48 GB pooled VRAMISV-certified Quadro drivers with enterprise support

For AI Workloads

Strengths
  • 24 GB ECC VRAM handles 13B FP16 and 30B Q4 inference reliably with error-correcting memory
  • NVLink allows two-card 48 GB pooled configuration for larger models
  • Mature driver support and enterprise certification for regulated production environments
  • Widely available used at significantly reduced prices relative to original MSRP
Considerations
  • Turing Tensor Cores lack FP8 β€” less efficient than Ada or Ampere workstation cards for quantized inference
  • PCIe 3.0 interface creates a modest host-to-device transfer bottleneck vs PCIe 4.0 cards
  • 32 TFLOPS FP16 is modest compared to Ampere and Ada workstation alternatives
  • Aging platform β€” enterprise driver support may be approaching end of life

Architecture

Turing

Turing is NVIDIA's first-generation RTX architecture, introducing dedicated RT and Tensor Cores to consumer GPUs for the first time. Built on TSMC's 12nm FinFET process.

AI Relevance

The first consumer architecture with Tensor Cores, enabling meaningful acceleration for INT8 and FP16 inference. However, limited VRAM (typically 6-11 GB) restricts modern LLM model sizes.

Process: TSMC 12nmPlatform: CUDATensor Cores: Gen 2Precisions: FP32, FP16, INT8, INT4

Recommendations by Workload

Chat

S

Qwen 3 14B

Qwen 3 14B matches Chat and keeps a practical fit profile. It is a recent-generation family, which helps on current local SOTA workloads. It fits natively with comfortable headroom. Context coverage stays within the requested workload envelope. Known distribution channels: huggingface, ollama, lm-studio.

Decode 45.8 tok/s Β· 60K ctx Β· llama.cppEST.
16.0 GB / 24.0 GB VRAM

Coding

S

Codestral 2 25.08

Codestral 2 25.08 is a specialized fit for Coding. It is a recent-generation family, which helps on current local SOTA workloads. It fits natively with comfortable headroom. Context coverage stays within the requested workload envelope. Known distribution channels: huggingface, lm-studio.

Decode 33.2 tok/s Β· 48K ctx Β· llama.cppEST.
19.2 GB / 24.0 GB VRAM

Agentic Coding

S

Full Model Compatibility

πŸ‘ Alibaba
Qwen3-Coder 30B A3B Instruct
S96
30.5B23.4 GB70 tok/s23K ctx
moe
πŸ‘ Alibaba
Qwen3-VL 30B A3B Instruct
S95
30B23.1 GB73 tok/s26K ctx
moe
πŸ‘ OpenAI
GPT-OSS 20B
S95

Just out of reach

Models you could run with an upgrade

High-quality models that need a bit more memory

Image & Video Generation

Diffusion Model Compatibility

41 of 52 models can generate images or video on your Quadro RTX 6000 24GB

ModelMax ResolutionGen TimeGrade
SD TurboImage512Γ—512~1.4sS
Stable Diffusion 1.5Image512Γ—768~2.8sS
Realistic Vision v5.1Image512Γ—768~2.8sS
DreamShaper 8Image512Γ—768~2.8sS
LCM DreamShaper v7

Upgrade paths

Upgrade from Quadro RTX 6000 24GB

See what you unlock with more powerful hardware

Upgrade options

Upgrade options

MacBook Pro M4 Max 36GBNext step up
36 GB Unified (+12)
A
Unlocks 1 additional models that do not fit on the current setup.Unlocks Gemma 4 31B

Unlocks 1 additional models that do not fit on the current setup.

~$2,499 MSRP

πŸ‘ NVIDIA
RTX 5000 Ada 32GBNVIDIA upgrade
32 GB VRAM (+8)
A
Unlocks 6 additional models that do not fit on the current setup.Unlocks Gemma 4 31B, Kimi Linear 48B A3B, Falcon 40B Instruct+3 more

Unlocks 6 additional models that do not fit on the current setup.

~$4,000 MSRP

Mac mini M4 64GBBest value
64 GB Unified (+40)
B
Unlocks 17 additional models that do not fit on the current setup.Unlocks Qwen 2.5 VL 72B, Gemma 4 31B, Llama 3.3 70B+14 more

Unlocks 17 additional models that do not fit on the current setup.

~$1,099 MSRP

AMD Instinct MI350X 288GBBiggest leap
288 GB VRAM (+264)8000 GB/s (+7328)
B
Unlocks 45 additional models that do not fit on the current setup.Unlocks Qwen 3.5 397B A17B, Devstral 2 123B Instruct, Qwen 3.5 122B A10B+42 more Β· +154% faster avg

Unlocks 45 additional models that do not fit on the current setup.

Lifts average decode speed across fitting models by about 154%.

~$8,000 MSRP

Frequently Asked Questions

Compare with similar

Quadro RTX 6000 24GB vs RTX 3090 24GBQuadro RTX 6000 24GB vs RTX 3090 Ti 24GBQuadro RTX 6000 24GB vs RTX 4090 24GB
Compare this GPUCompare with another GPU β†’
24
GB
VRAM
672GB/s
Bandwidth
32TFLOPS
FP16 Compute
256TOPS
INT8 Inference
$4,000 MSRP
Quadro RTX 6000 24GBCategory AvgMacBook Pro M4 Max 36GB
Won’t fit
Llama 3.1 70B Q4
β€”
Image Gen (SDXL)Runs nativelySDXL 1.0 FP16~~11.3s per image
Image Gen (Flux)Runs with offloadFlux.1 Dev FP16~~50.8s per image
Image Gen (SD 3.5)Runs nativelySD 3.5 Large FP16~~1m 2s per image
Video Short (25f)Runs nativelyLTX Video 2B~~9.8s/frame
Video Long (100f)Won't fitWan Video 14B~~28.9s/frame

Qwen 3.6 27B

Qwen 3.6 27B is a specialized fit for Agentic Coding. It is a recent-generation family, which helps on current local SOTA workloads. It should run, but memory headroom will be limited. Context coverage stays within the requested workload envelope. Known distribution channels: huggingface, lm-studio.

Decode 23.1 tok/s Β· 69K ctx Β· llama.cppEST.
21.7 GB / 24.0 GB VRAM

Reasoning

S

Devstral Small 2 24B Instruct

Devstral Small 2 24B Instruct matches Reasoning and keeps a practical fit profile. It is a recent-generation family, which helps on current local SOTA workloads. It should run, but memory headroom will be limited. Context coverage stays within the requested workload envelope. Known distribution channels: huggingface, ollama, lm-studio.

Decode 34.0 tok/s Β· 40K ctx Β· llama.cppEST.
20.4 GB / 24.0 GB VRAM

RAG

A

Granite 4.1 8B

Granite 4.1 8B matches RAG and keeps a practical fit profile. It sits in the middle of the current generation mix. It fits natively with comfortable headroom. Context coverage stays within the requested workload envelope. Known distribution channels: huggingface, ollama.

Decode 79.8 tok/s Β· 93K ctx Β· llama.cppEST.
14.7 GB / 24.0 GB VRAM
21B18.6 GB89 tok/s52K ctx
moe
πŸ‘ Alibaba
Qwen 3 14B
S94
14B14.3 GB59 tok/s80K ctx
dense
πŸ‘ Microsoft
Phi-4-reasoning-plus 14B
S94
14.7B15.3 GB56 tok/s33K ctx
dense
πŸ‘ Alibaba
Qwen 3 30B A3B
S94
30.5B23.4 GB70 tok/s23K ctx
moe
πŸ‘ Alibaba
Qwen 3.5 9B
S93
9B11.0 GB91 tok/s111K ctx
dense
πŸ‘ Alibaba
Qwen 3.5 27B
S93
27B22.9 GB30 tok/s21K ctx
dense
πŸ‘ Mistral
Magistral Small 2507
S92
24B20.4 GB34 tok/s40K ctx
dense
πŸ‘ Mistral
Devstral Small 2 24B Instruct
S92
24B20.4 GB34 tok/s40K ctx
dense
πŸ‘ Alibaba
Qwen 3.6 27B
S92
27B20.7 GB23 tok/s69K ctx
+1dense
πŸ‘ Alibaba
Qwen 3 8B
S91
8B10.4 GB102 tok/s115K ctx
dense
πŸ‘ Mistral
Devstral Small 1.1
S90
24B20.4 GB34 tok/s40K ctx
dense
πŸ‘ NVIDIA
Nemotron Cascade 2 30B A3B
S90
30B24.5 GB50 tok/s13K ctx
moe
πŸ‘ NVIDIA
Nemotron 3 Nano 30B
S89
30B24.0 GB20 tok/s16K ctx
dense
πŸ‘ Google
Gemma 4 26B A4B
S88
25.2B22.3 GB75 tok/s23K ctx
moe
πŸ‘ Mistral
Ministral 3 14B
S88
14B14.3 GB58 tok/s80K ctx
multimodal
πŸ‘ Alibaba
Qwen 3.5 4B
S87
4B7.9 GB56 tok/s131K ctx
dense
πŸ‘ NVIDIA
Nemotron Nano 8B
S86
8B10.1 GB102 tok/s130K ctx
dense
πŸ‘ Microsoft
Phi-4 Mini Reasoning 4B
A84
3.8B7.1 GB53 tok/s131K ctx
dense
πŸ‘ Alibaba
Qwen 3.5 35B A3B
A83
35B26.1 GB39 tok/s4K ctx
moe
πŸ‘ Alibaba
Qwen 3 32B
A79
32B26.7 GB15 tok/s5K ctx
dense
πŸ‘ Jina AI
Jina Embeddings v3
A77
0.57B6.4 GB8 tok/s8K ctx
dense
πŸ‘ Alibaba
Qwen 3.6 35B A3B
A76
35B28.8 GB29 tok/s4K ctx
+1moe
πŸ‘ BAAI
BGE M3
A75
0.57B5.6 GB8 tok/s8K ctx
dense
πŸ‘ LG AI
EXAONE 4.0 32B
A73
32B26.7 GB15 tok/s5K ctx
dense
πŸ‘ Alibaba
Qwen 3.5 397B A17B
F0
397B248.3 GB2 tok/s4K ctx
moe
πŸ‘ Mistral
Devstral 2 123B Instruct
F0
123B83.7 GB2 tok/s4K ctx
dense
πŸ‘ Moonshot AI
Kimi K2.5
F0
1000B620.7 GB2 tok/s4K ctx
moe
πŸ‘ Moonshot AI
Kimi K2.6
F0
1000B620.7 GB2 tok/s4K ctx
+1moe
πŸ‘ DeepSeek
DeepSeek V4 Pro
F0
1600B867.2 GB2 tok/s4K ctx
moe
πŸ‘ Alibaba
Qwen 3.5 122B A10B
F0
122B80.2 GB3 tok/s4K ctx
moe
πŸ‘ DeepSeek
DeepSeek V4 Flash
F0
284B162.6 GB2 tok/s4K ctx
moe
πŸ‘ Mistral
Mistral Small 4 119B
F0
119B81.3 GB3 tok/s4K ctx
moe
πŸ‘ Cohere
Command A 111B
F0
111B74.9 GB2 tok/s4K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 VL 72B
F0
72B52.1 GB2 tok/s4K ctx
dense
πŸ‘ OpenAI
GPT-OSS 120B
F0
117B79.6 GB2 tok/s4K ctx
dense
πŸ‘ Alibaba
Qwen3-Coder-Next
F0
80B53.6 GB5 tok/s4K ctx
moe
πŸ‘ Z.ai
GLM-5.1
F0
754B482.3 GB2 tok/s4K ctx
moe
πŸ‘ Mistral AI
Pixtral Large 124B
F0
124B84.3 GB2 tok/s4K ctx
dense
πŸ‘ Z.ai
GLM-5
F0
744B476.2 GB2 tok/s4K ctx
moe
πŸ‘ DeepSeek
DeepSeek V3.2
F0
671B413.1 GB2 tok/s4K ctx
moe
πŸ‘ Alibaba
Qwen 3 235B A22B
F0
235B149.5 GB2 tok/s4K ctx
moe
πŸ‘ Alibaba
Qwen3-Coder 480B A35B Instruct
F0
480B299.0 GB2 tok/s4K ctx
moe
πŸ‘ Google
Gemma 4 31B
F0
30.7B36.7 GB6 tok/s4K ctx
dense
MiniMax M2.7
F0
230B147.4 GB2 tok/s4K ctx
moe
πŸ‘ Mistral
Leanstral 119B A6B
F0
119B84.7 GB3 tok/s4K ctx
moe
πŸ‘ DeepSeek
DeepSeek Coder V2 236B
F0
236B205.9 GB2 tok/s4K ctx
moe
πŸ‘ DeepSeek
DeepSeek R1 671B
F0
671B472.2 GB2 tok/s4K ctx
moe
πŸ‘ DeepSeek
DeepSeek V3.1 671B
F0
671B472.2 GB2 tok/s4K ctx
moe
Image
512Γ—768
800ms
S
PixArt-SigmaImage1024Γ—1024~11.3sS
FramePack I2VVideo256Γ—256~20.7s/frameS
SDXL TurboImage512Γ—512~1.4sS
SDXL LightningImage1024Γ—1024~4.2sS
Stable Diffusion XL 1.0Image1024Γ—1024~11.3sS
Playground v2.5Image1024Γ—1024~16.9sS
RealVisXL v5.0Image1024Γ—1024~12.7sS
DreamShaper XLImage1024Γ—1024~12.7sS
Juggernaut XL v9Image1024Γ—1024~12.7sS
Animagine XL 3.1Image1024Γ—1024~12.7sS
Pony Diffusion V6 XLImage1024Γ—1024~12.7sS
Animagine XL 4.0Image1024Γ—1024~12.7sS
Illustrious XLImage1024Γ—1024~12.7sS
Wan Video 2.1 1.3BVideo256Γ—256~8.3s/frameS
Stable Diffusion 3.5 MediumImage1024Γ—1024~19.8sS
Flux.2 Klein 4BImage1024Γ—1024~3.4sS
LTX Video 2BVideo768Γ—512~9.8s/frameS
KolorsImage1024Γ—1024~22.6sS
Stable CascadeImage1024Γ—1024~28.2sS
AuraFlow v0.3Image1536Γ—1536~50.8sS
Stable Diffusion 3.5 LargeImage1024Γ—1024~1m 2sS
Stable Diffusion 3.5 Large TurboImage1024Γ—1024~11.3sS
CogVideoX 2BVideo720Γ—480~9.8s/frameA
HunyuanVideoVideo256Γ—256~20.7s/frameA
ChromaImage256Γ—256~20.7sA
Z-Image TurboImage1536Γ—1536~11.6sB
Flux.1 DevImage256Γ—256~50.8sB
Flux.1 SchnellImage256Γ—256~9.9sB
LTX Video 13BVideo256Γ—256~20.7s/frameB
Flux.1 Kontext DevImage256Γ—256~56.4sB
AnimateDiff v1.5.3Video512Γ—768~5.1s/frameB
Cosmos Diffusion 7BVideo256Γ—256~31.2s/frameB
CogVideoX 5BVideo256Γ—256~29.7s/frameB
Wan2.2 TI2V 5BVideo256Γ—256~29.7s/frameB
Flux.2 Klein 9BImage256Γ—256~10.3sD
Flux.1 Fill DevImage256Γ—256~48sD
Mochi 1 PreviewVideo256Γ—256~18.7s/frameF
HunyuanVideo 1.5Video256Γ—256~17.3s/frameF
Helios 14BVideo256Γ—256~21.3s/frameF
SkyReels V2 14BVideo256Γ—256~21.3s/frameF
Wan Video 2.1 14BVideo256Γ—256~21.3s/frameF
Wan Video 2.2 14BVideo256Γ—256~21.3s/frameF
Qwen ImageImage256Γ—256~19sF
Qwen Image EditImage256Γ—256~19sF
Flux.2 DevImage256Γ—256~8m 54sF
MAGI-1Video256Γ—256~26.5s/frameF
HunyuanImage 3.0Image256Γ—256~33.5sF

Image models estimated at 1024Γ—1024 (28 steps, FP16). Video models estimated at 768Γ—512 (25 frames, 30 steps, FP16). Actual performance varies with runtime and system load.

Buying advice

Should you buy Quadro RTX 6000 24GB for local AI?

Excellent choice for local AI

Runs 26 of 50 top models well β€” a strong all-rounder for local inference.

24.0 GB

VRAM

$4,000

MSRP

$167/GB

Cost per GB VRAM

Best models for this GPU

What will limit you first

This setup is broadly balanced for this model.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Older PCIe generation

PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.

Best upgrade itinerary

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Unlocks 1 additional models that do not fit on the current setup.

Want more headroom? MacBook Pro M4 Max 36GB (36.0 GB unified memory) is the next step up.