What can NVIDIA GeForce RTX 4080 Super run locally?

101 models fit comfortably on NVIDIA GeForce RTX 4080 Super with 32 GB system RAM. 94 more run with tradeoffs. Top pick: Ministral 3B Instruct.

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 long context?

Build: RTX 4080 Super + i7-14700K + 32GB DDR5

Memory: 16 GB VRAM + 32 GB system RAM

Runner: llama.cpp / Ollama (CUDA)

Any Chat Coding Agents Reasoning Vision Long context Creative

Runs comfortably
101 models

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

#1Ministral 3B Instruct

mistral

Quant: Q4_K_MContext: 8,192VRAM: 5.3 GBHeadroom: 10.7 GBTTFT: fast

264

tok/s

Estimated

Weights

1.90 GB

KV cache

1.50 GB

Activations

0.10 GB

Runtime

1.80 GB

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

Model details →

#2Phi-3.5 Mini Instruct

3.8B

phi

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 8.0 GBHeadroom: 8.0 GBTTFT: fast

ollama run phi3.5:3.8b

118

tok/s

Estimated

Weights

4.10 GB

KV cache

1.90 GB

Activations

0.21 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~186 ms (fast)

Model details →

#3Falcon Mamba 7B

falcon

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 6.3 GBTTFT: fast

113

tok/s

Estimated

Weights

4.20 GB

KV cache

3.50 GB

Activations

0.22 GB

Runtime

1.80 GB

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

Model details →

#4Codestral Mamba 7B

mistral

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 6.3 GBTTFT: fast

113

tok/s

Estimated

Weights

4.20 GB

KV cache

3.50 GB

Activations

0.22 GB

Runtime

1.80 GB

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

Model details →

#5Gemma 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 →

#6Qwen 3 8B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 10.8 GBHeadroom: 5.2 GBTTFT: fast

ollama run qwen3:8b

tok/s

Estimated

Weights

4.80 GB

KV cache

4.00 GB

Activations

0.25 GB

Runtime

1.80 GB

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

Model details →

#7Command R7B (12-2024)

command-r

Quant: Q4_K_MContext: 8,192VRAM: 10.4 GBHeadroom: 5.6 GBTTFT: fast

tok/s

Estimated

Weights

4.40 GB

KV cache

4.00 GB

Activations

0.23 GB

Runtime

1.80 GB

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

Model details →

#8Ministral 8B Instruct

mistral

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 →

#9Qwen 2.5 7B Instruct

qwen

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 5.2 GBTTFT: fast

ollama run qwen2.5:7b

tok/s

Estimated

Weights

8.10 GB

KV cache

0.47 GB

Activations

0.41 GB

Runtime

1.80 GB

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

Model details →

#10Llama 3.1 8B Instruct

llama

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 11.8 GBHeadroom: 4.2 GBTTFT: fast

ollama run llama3.1:8b

tok/s

Estimated

Weights

8.50 GB

KV cache

1.07 GB

Activations

0.43 GB

Runtime

1.80 GB

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

Model details →

#11InternLM 2.5 7B Chat

internlm

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 →

#12Turkish Mistral 7B Instruct v0.2

mistral

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 9.4 GBHeadroom: 6.6 GBTTFT: fast

113

tok/s

Estimated

Weights

3.90 GB

KV cache

3.50 GB

Activations

0.20 GB

Runtime

1.80 GB

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

Model details →

Runs with tradeoffs
94 models

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

Mistral Nemo 12B Instruct

12B

mistral

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 15.7 GBHeadroom: 0.3 GBTTFT: noticeable

• Tight VRAM fit — only 0.3 GB headroom left for context growth

ollama run mistral-nemo:12b

tok/s

Estimated

Weights

7.50 GB

KV cache

6.00 GB

Activations

0.38 GB

Runtime

1.80 GB

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

Model details →

Qwen 3 14B

14B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 12.4 GBHeadroom: 3.6 GBTTFT: noticeable

• Tight VRAM fit — only 3.6 GB headroom left for context growth

ollama run qwen3:14b

tok/s

Estimated

Weights

8.40 GB

KV cache

1.75 GB

Activations

0.42 GB

Runtime

1.80 GB

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

Model details →

Qwen 2.5 14B Instruct

14B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 12.9 GBHeadroom: 3.1 GBTTFT: noticeable

• Tight VRAM fit — only 3.1 GB headroom left for context growth

ollama run qwen2.5:14b

tok/s

Estimated

Weights

8.90 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 →

DeepSeek V2 Lite Chat

15.7B

deepseek

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 12.8 GBHeadroom: 3.2 GBTTFT: fast

• Tight VRAM fit — only 3.2 GB headroom left for context growth

330

tok/s

Estimated

Weights

8.60 GB

KV cache

1.96 GB

Activations

0.43 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~118 ms (fast)

Model details →

Phi-4 14B

14B

phi

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 12.4 GBHeadroom: 3.6 GBTTFT: noticeable

• Tight VRAM fit — only 3.6 GB headroom left for context growth

ollama run phi4:14b

tok/s

Estimated

Weights

8.40 GB

KV cache

1.75 GB

Activations

0.42 GB

Runtime

1.80 GB

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

Model details →

Nemotron 3 Nano (30B-A3B)

30B

other

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 24.5 GBHeadroom: 10.7 GBTTFT: noticeable

• Partial CPU offload: ~35% of layers run on CPU
• CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here

ollama run nemotron3:nano

tok/s

Estimated

Weights

18.00 GB

KV cache

3.75 GB

Activations

0.90 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1471 ms (noticeable)

Model details →

Granite 3 MoE (3B active)

16B

granite

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 13.8 GBHeadroom: 2.2 GBTTFT: fast

• Tight VRAM fit — only 2.2 GB headroom left for context growth

264

tok/s

Estimated

Weights

9.50 GB

KV cache

2.00 GB

Activations

0.48 GB

Runtime

1.80 GB

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

Model details →

DeepSeek V3 Lite (16B MoE)

16B

deepseek

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 13.8 GBHeadroom: 2.2 GBTTFT: fast

• Tight VRAM fit — only 2.2 GB headroom left for context growth

330

tok/s

Estimated

Weights

9.50 GB

KV cache

2.00 GB

Activations

0.48 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~118 ms (fast)

Model details →

What if you upgraded?

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

+32 GB system RAM

~$80–150

Doubles your CPU-offload working set. Helps when models don't quite fit in VRAM.

Unlocks: 41 new comfortable, 112 new tradeoff

• Qwen 3 0.6B
• Qwen 3 1.7B
• Gemma 3 270M
• SmolLM2 135M Instruct

Shop this upgrade↗

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

~$350

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

Unlocks: 68 new comfortable

• Qwen 3 0.6B
• Gemma 4 12B
• Qwen3.5 9B
• Qwen 3 1.7B

Shop this upgrade↗

Add a second NVIDIA GeForce RTX 4080 Super

~$1099

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: 115 new comfortable

• Qwen 3 0.6B
• Qwen 3 30B-A3B
• Qwen 2.5 Coder 32B Instruct
• Qwen3.6 27B

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