What can NVIDIA GeForce RTX 4080 Super run locally?

14 models fit comfortably on NVIDIA GeForce RTX 4080 Super with 32 GB system RAM. 14 more run with tradeoffs. Top pick: Gemma 4 E2B (Effective 2B).

What's the recommended runner for this hardware?

llama.cpp / Ollama (CUDA). This is the runner that gives best tokens-per-second on NVIDIA GeForce RTX 4080 Super based on windows support and the GPU backend.

What can NVIDIA GeForce RTX 4080 Super run for vision?

Build: NVIDIA GeForce RTX 4080 Super + — + 32 GB RAM (windows)

Memory: 16 GB VRAM + 32 GB system RAM

Runner: llama.cpp / Ollama (CUDA)

Any Chat Coding Agents Reasoning Vision Long context Creative

Runs comfortably
14 models

Ranked by fit for vision use case + predicted speed. Click a row for VRAM breakdown.

#1Gemma 4 E2B (Effective 2B)

gemma

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 5.1 GBHeadroom: 10.9 GBTTFT: instant

ollama run gemma4:e2b

225

tok/s

Estimated

Weights

2.20 GB

KV cache

1.00 GB

Activations

0.12 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~98 ms (instant)

Model details →

#2Phi-3.5 Vision

4.2B

phi

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 6.5 GBHeadroom: 9.5 GBTTFT: fast

189

tok/s

Estimated

Weights

2.50 GB

KV cache

2.10 GB

Activations

0.13 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~206 ms (fast)

Model details →

#3Moondream 2

1.9B

other

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 3.3 GBHeadroom: 12.7 GBTTFT: instant

417

tok/s

Estimated

Weights

1.20 GB

KV cache

0.24 GB

Activations

0.06 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~93 ms (instant)

Model details →

#4Qwen 2.5-VL 3B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 5.4 GBHeadroom: 10.6 GBTTFT: fast

264

tok/s

Estimated

Weights

2.00 GB

KV cache

1.50 GB

Activations

0.11 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~147 ms (fast)

Model details →

#5Qwen 2.5-VL 7B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 6.1 GBTTFT: fast

113

tok/s

Estimated

Weights

4.40 GB

KV cache

3.50 GB

Activations

0.23 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~343 ms (fast)

Model details →

#6Qwen 2-VL 7B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 5.9 GBTTFT: fast

113

tok/s

Estimated

Weights

4.60 GB

KV cache

3.50 GB

Activations

0.24 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~343 ms (fast)

Model details →

#7LLaVA 1.6 Mistral 7B

other

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 10.0 GBHeadroom: 6.0 GBTTFT: fast

113

tok/s

Estimated

Weights

4.50 GB

KV cache

3.50 GB

Activations

0.23 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~343 ms (fast)

Model details →

#8LLaVA-OneVision 7B

other

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 10.0 GBHeadroom: 6.0 GBTTFT: fast

113

tok/s

Estimated

Weights

4.50 GB

KV cache

3.50 GB

Activations

0.23 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~343 ms (fast)

Model details →

#9Gemma 4 E4B (Effective 4B)

gemma

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 8.4 GBHeadroom: 7.6 GBTTFT: fast

ollama run gemma4:e4b

113

tok/s

Estimated

Weights

4.40 GB

KV cache

2.00 GB

Activations

0.23 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~196 ms (fast)

Model details →

#10Gemma 3 4B

gemma

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 8.4 GBHeadroom: 7.6 GBTTFT: fast

ollama run gemma3:4b

113

tok/s

Estimated

Weights

4.40 GB

KV cache

2.00 GB

Activations

0.23 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~196 ms (fast)

Model details →

#11MiniCPM-V 2.6 8B

minicpm

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 11.1 GBHeadroom: 4.9 GBTTFT: fast

tok/s

Estimated

Weights

5.00 GB

KV cache

4.00 GB

Activations

0.26 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~392 ms (fast)

Model details →

#12MiniCPM-V 3 8B

minicpm

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 11.1 GBHeadroom: 4.9 GBTTFT: fast

tok/s

Estimated

Weights

5.00 GB

KV cache

4.00 GB

Activations

0.26 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~392 ms (fast)

Model details →

Runs with tradeoffs
14 models

Tight VRAM, partial CPU offload, or context-limited.

Llama 3.2 11B Vision Instruct

11B

llama

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 15.6 GBHeadroom: 0.4 GBTTFT: noticeable

• Tight VRAM fit — only 0.4 GB headroom left for context growth

ollama run llama3.2-vision:11b

tok/s

Estimated

Weights

7.90 GB

KV cache

5.50 GB

Activations

0.40 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~539 ms (noticeable)

Model details →

Llama 3.2 11B Vision

11B

llama

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 14.1 GBHeadroom: 1.9 GBTTFT: noticeable

• Tight VRAM fit — only 1.9 GB headroom left for context growth

tok/s

Estimated

Weights

6.50 GB

KV cache

5.50 GB

Activations

0.33 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~539 ms (noticeable)

Model details →

Gemma 3 12B

12B

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 15.5 GBHeadroom: 0.5 GBTTFT: noticeable

• Tight VRAM fit — only 0.5 GB headroom left for context growth

ollama run gemma3:12b

tok/s

Estimated

Weights

7.30 GB

KV cache

6.00 GB

Activations

0.37 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~589 ms (noticeable)

Model details →

Pixtral 12B

12B

mistral

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 15.2 GBHeadroom: 0.8 GBTTFT: noticeable

• Tight VRAM fit — only 0.8 GB headroom left for context growth

ollama run pixtral:12b

tok/s

Estimated

Weights

7.00 GB

KV cache

6.00 GB

Activations

0.36 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~589 ms (noticeable)

Model details →

GLM-4V 9B

13.9B

glm

Quant: Q4_K_MContext: 2,048VRAM: 12.5 GBHeadroom: 3.5 GBTTFT: noticeable

• Tight VRAM fit — only 3.5 GB headroom left for context growth

tok/s

Estimated

Weights

8.50 GB

KV cache

1.74 GB

Activations

0.43 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~682 ms (noticeable)

Model details →

Phi-4 Multimodal

14B

phi

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 13.0 GBHeadroom: 3.0 GBTTFT: noticeable

• Tight VRAM fit — only 3.0 GB headroom left for context growth

tok/s

Estimated

Weights

9.00 GB

KV cache

1.75 GB

Activations

0.45 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~687 ms (noticeable)

Model details →

Trendyol LLM Asure 12B

11.8B

gemma

Commercial OK

Quant: GGUF_UNKNOWNContext: 8,192VRAM: 12.7 GBHeadroom: 3.3 GBTTFT: noticeable

• Tight VRAM fit — only 3.3 GB headroom left for context growth

ollama run alibayram/Trendyol-LLM-Asure-12B:latest

tok/s

Estimated

Weights

7.30 GB

KV cache

3.22 GB

Activations

0.37 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~579 ms (noticeable)

Model details →

Gemma 4 26B MoE

26B

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 31.6 GBHeadroom: 3.6 GBTTFT: noticeable

• Partial CPU offload: ~49% of layers run on CPU

ollama run gemma4:26b-moe

tok/s

Estimated

Weights

16.00 GB

KV cache

13.00 GB

Activations

0.81 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1275 ms (noticeable)

Model details →

What if you upgraded?

Hypothetical scenarios. We re-ran the compatibility engine for each.

+32 GB system RAM

Check the current price

Adds 32 GB to your CPU-offload working set. Helps when models don't quite fit in VRAM.

Unlocks: 83 new comfortable, 78 new tradeoff

• Qwen 3 0.6B
• Llama 3.1 8B Instruct
• Qwen 3 8B
• Qwen 3 1.7B

Shop this upgrade↗

Upgrade to NVIDIA RTX 2080 Ti 22GB (China-mod)

Check the current price

22 GB VRAM (vs your 16 GB) plus a bandwidth jump from ~736 GB/s to ~616 GB/s.

Unlocks: 102 new comfortable

• Qwen 3 0.6B
• Llama 3.1 8B Instruct
• Qwen 3 8B
• Qwen 3 1.7B

Add a second NVIDIA GeForce RTX 4080 Super

Launch MSRP $999 (2024). Check the current price.

Tensor parallelism splits the model across both cards, effectively doubling VRAM. Bandwidth doesn't double — runs ~1.5× the single-card speed in practice.

Unlocks: 133 new comfortable

• Qwen 3 0.6B
• Llama 3.1 8B Instruct
• Qwen 3 30B-A3B
• Qwen 2.5 Coder 32B Instruct

Shop this upgrade↗

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

Won't run
top 5 popular models

Need more memory than you have. Shown for orientation.

DeepSeek V4 Pro (1.6T MoE)

1600B

deepseek

Commercial OK