Advanced tool

Answers: How to plan a specific technical model configuration on your GPU.

Does not answer: What RigFact has actually captured evidence for, or what you should run.

What can I do with my GPU? →

Recipe Planner

Experimental tool

Use this when you already know the model and configuration you want to plan. Choose your GPU and the context size you need. RigFact compares verified Ollama model recipes and shows which ones are estimated below or above your GPU's nominal VRAM.

For the simpler question “What can I do with my GPU?”, use the main RigFact journey — linked at the top of this page.

How does this work?

• GPU memory comes from source-verified NVIDIA specifications.

• Model recipes use exact curated GGUF artifacts from verified sources.

• Memory estimates come from source-backed, versioned estimators selected for each model architecture.

• Some standard models use the versioned Ollama estimator; hybrid architectures may use a separately validated analytical model.

• The result is an estimate, not proof that a model will run.

Context = how much information the model can work with at one time. A larger context uses more memory and is not automatically the right choice for every task.

Captured run = a RigFact test run we recorded.Planning estimate = a planning figure only, not captured workload evidence.

GPU
NVIDIA GeForce RTX 3090
24 GB GDDR6X
Source: NVIDIA
Requested context
2,048 tokens
NVIDIA GeForce RTX 3090: 24 GB GDDR6X.
Memory estimate covers model weights and modeled context memory. Runtime compute/graph overhead is not included, so this is an analytical estimate — not a guarantee of device residency.

Estimated below nominal capacity

Mistral Small 22BPlanning estimate
q4_K_M · Runtime: Ollama
Estimated to fit
No direct evidence yet
Related evidence available
· Curated observation
Independence of sources not established
Estimated memory
12.9 GiB
GPU capacity
22.4 GiB
(24 GB advertised)
Nominal headroom: ~9.5 GiB before runtime overhead.
Gemma 2 27BPlanning estimate
q4_K_M · Runtime: Ollama
Estimated to fit
No direct evidence yet
Estimated memory
16.3 GiB
GPU capacity
22.4 GiB
(24 GB advertised)
Nominal headroom: ~6.0 GiB before runtime overhead.
Qwen3 8BPlanning estimate
q4_K_M · Runtime: Ollama
Estimated to fit
No direct evidence yet
Estimated memory
5.1 GiB
GPU capacity
22.4 GiB
(24 GB advertised)
Nominal headroom: ~17.2 GiB before runtime overhead.
Qwen3 14BPlanning estimate
q4_K_M · Runtime: Ollama
Estimated to fit
No direct evidence yet
Estimated memory
9.0 GiB
GPU capacity
22.4 GiB
(24 GB advertised)
Nominal headroom: ~13.4 GiB before runtime overhead.
Qwen3 32BPlanning estimate
q4_K_M · Runtime: Ollama
Estimated to fit
No direct evidence yet
Estimated memory
19.1 GiB
GPU capacity
22.4 GiB
(24 GB advertised)
Nominal headroom: ~3.2 GiB before runtime overhead.
Qwen3 30B (A3B)Planning estimate
q4_K_M · Runtime: Ollama
Estimated to fit
No direct evidence yet
Estimated memory
17.4 GiB
GPU capacity
22.4 GiB
(24 GB advertised)
Nominal headroom: ~5.0 GiB before runtime overhead.
Qwen3.6 35B A3B (UD-IQ4_NL)Planning estimate
UD-IQ4_NL · Runtime: Ollama
Estimated to fit
No direct evidence yet
Estimated memory
16.9 GiB
GPU capacity
22.4 GiB
(24 GB advertised)
Nominal headroom: ~5.4 GiB before runtime overhead.

Estimated above nominal capacity

Llama 3.3 70BPlanning estimate
q4_K_M · Runtime: Ollama
Estimated over capacity
No direct evidence yet
Estimated memory
40.2 GiB
GPU capacity
22.4 GiB
(24 GB advertised)
Other options that fit this GPU
Mistral Small 22B · q4_K_M · ~12.9 GiB
Gemma 2 27B · q4_K_M · ~16.3 GiB
Qwen3 8B · q4_K_M · ~5.1 GiB
Qwen3 14B · q4_K_M · ~9.0 GiB
Qwen3 32B · q4_K_M · ~19.1 GiB
Qwen3 30B (A3B) · q4_K_M · ~17.4 GiB
Qwen3.6 35B A3B (UD-IQ4_NL) · UD-IQ4_NL · ~16.9 GiB
Can't run it locally? Run on a cloud GPU:
Vast.aiRunPod

Affiliate links — we may earn a commission at no extra cost to you.

DeepSeek V3 671BPlanning estimate
q4_K_M · Runtime: Ollama
Estimated over capacity
No direct evidence yet
Estimated memory
380.0 GiB
GPU capacity
22.4 GiB
(24 GB advertised)
Other options that fit this GPU
Mistral Small 22B · q4_K_M · ~12.9 GiB
Gemma 2 27B · q4_K_M · ~16.3 GiB
Qwen3 8B · q4_K_M · ~5.1 GiB
Qwen3 14B · q4_K_M · ~9.0 GiB
Qwen3 32B · q4_K_M · ~19.1 GiB
Qwen3 30B (A3B) · q4_K_M · ~17.4 GiB
Qwen3.6 35B A3B (UD-IQ4_NL) · UD-IQ4_NL · ~16.9 GiB
Can't run it locally? Run on a cloud GPU:
Vast.aiRunPod

Affiliate links — we may earn a commission at no extra cost to you.

Estimator results are analytical estimates relative to vendor nominal capacity — not proof of device fit. First-party recipes are real measured runs on the named captured hardware.

Check your GPU's memory against available models →