What can NVIDIA RTX 2080 Ti 22GB (China-mod) run locally?

88 models fit comfortably on NVIDIA RTX 2080 Ti 22GB (China-mod) with 32 GB system RAM. 46 more run with tradeoffs. Top pick: CodeGemma 7B.

What's the recommended runner for this hardware?

llama.cpp / Ollama (CUDA). This is the runner that gives best tokens-per-second on NVIDIA RTX 2080 Ti 22GB (China-mod) based on windows support and the GPU backend.

What can NVIDIA RTX 2080 Ti 22GB (China-mod) run for coding?

Build: NVIDIA RTX 2080 Ti 22GB (China-mod) + — + 32 GB RAM (windows)

Memory: 22 GB VRAM + 32 GB system RAM

Runner: llama.cpp / Ollama (CUDA)

Any Chat Coding Agents Reasoning Vision Long context Creative

Runs comfortably
88 models

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

#1CodeGemma 7B

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 12.3 GBTTFT: noticeable

ollama run codegemma:7b

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): ~666 ms (noticeable)

Model details →

#2Qwen 3 14B

14B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 4.4 GBTTFT: noticeable

ollama run qwen3:14b

tok/s

Estimated

Weights

8.40 GB

KV cache

7.00 GB

Activations

0.43 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1332 ms (noticeable)

Model details →

#3Qwen 2.5 7B Instruct

qwen

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 11.2 GBTTFT: noticeable

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): ~666 ms (noticeable)

Model details →

#4Llama 3.1 8B Instruct

llama

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 11.8 GBHeadroom: 10.2 GBTTFT: noticeable

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): ~761 ms (noticeable)

Model details →

#5Qwen 3 8B

qwen

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 14.4 GBHeadroom: 7.6 GBTTFT: noticeable

ollama run qwen3:8b

tok/s

Estimated

Weights

8.20 GB

KV cache

4.00 GB

Activations

0.42 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~761 ms (noticeable)

Model details →

#6Qwen 2.5 Coder 3B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 5.3 GBHeadroom: 16.7 GBTTFT: fast

221

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): ~286 ms (fast)

Model details →

#7StarCoder 2 3B

other

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 5.4 GBHeadroom: 16.6 GBTTFT: fast

221

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): ~286 ms (fast)

Model details →

#8Codestral Mamba 7B

mistral

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 12.3 GBTTFT: noticeable

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): ~666 ms (noticeable)

Model details →

#9StarCoder 2 7B

other

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 12.1 GBTTFT: noticeable

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): ~666 ms (noticeable)

Model details →

#10OpenCoder 8B

opencoder

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 11.3 GBTTFT: noticeable

tok/s

Estimated

Weights

4.70 GB

KV cache

4.00 GB

Activations

0.24 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~761 ms (noticeable)

Model details →

#11Yi Coder 9B

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 12.0 GBHeadroom: 10.0 GBTTFT: noticeable

tok/s

Estimated

Weights

5.40 GB

KV cache

4.50 GB

Activations

0.28 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~857 ms (noticeable)

Model details →

#12Qwen 2.5 Coder 14B Instruct

14B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 4.4 GBTTFT: noticeable

tok/s

Estimated

Weights

8.40 GB

KV cache

7.00 GB

Activations

0.43 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1332 ms (noticeable)

Model details →

Runs with tradeoffs
46 models

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

DeepSeek Coder V2 Lite (16B)

16B

deepseek

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 19.8 GBHeadroom: 2.2 GBTTFT: noticeable

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

ollama run deepseek-coder-v2:16b

tok/s

Estimated

Weights

9.50 GB

KV cache

8.00 GB

Activations

0.48 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1523 ms (noticeable)

Model details →

Codestral 22B

22B

mistral

Quant: Q4_K_MContext: 2,048VRAM: 18.2 GBHeadroom: 3.8 GBTTFT: slow

• Tight VRAM fit — only 3.8 GB headroom left for context growth

ollama run codestral:22b

tok/s

Estimated

Weights

13.00 GB

KV cache

2.75 GB

Activations

0.65 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~2094 ms (slow)

Model details →

Qwen 2.5 14B Instruct

14B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 18.2 GBHeadroom: 3.8 GBTTFT: noticeable

• Tight VRAM fit — only 3.8 GB headroom left for context growth

ollama run qwen2.5:14b

tok/s

Estimated

Weights

8.90 GB

KV cache

7.00 GB

Activations

0.45 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1332 ms (noticeable)

Model details →

Qwen 2.5 Coder 32B Instruct

32B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 23.9 GBHeadroom: 17.3 GBTTFT: slow

• Partial CPU offload: ~8% of layers run on CPU

ollama run qwen2.5-coder:32b

tok/s

Estimated

Weights

19.00 GB

KV cache

2.15 GB

Activations

0.96 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~3045 ms (slow)

Model details →

Qwen 3 30B-A3B

30B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 35.7 GBHeadroom: 5.5 GBTTFT: slow

• Partial CPU offload: ~38% of layers run on CPU

ollama run qwen3:30b

tok/s

Estimated

Weights

18.00 GB

KV cache

15.00 GB

Activations

0.91 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~2855 ms (slow)

Model details →

Gemma 4 31B Dense

31B

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 36.2 GBHeadroom: 5.0 GBTTFT: slow

• Partial CPU offload: ~39% of layers run on CPU

ollama run gemma4:31b

tok/s

Estimated

Weights

18.00 GB

KV cache

15.50 GB

Activations

0.91 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~2950 ms (slow)

Model details →

Qwen 3 32B

32B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 37.8 GBHeadroom: 3.4 GBTTFT: slow

• Partial CPU offload: ~42% of layers run on CPU

ollama run qwen3:32b

tok/s

Estimated

Weights

19.00 GB

KV cache

16.00 GB

Activations

0.96 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~3045 ms (slow)

Model details →

Qwen 2.5 32B Instruct

32B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 37.8 GBHeadroom: 3.4 GBTTFT: slow

• Partial CPU offload: ~42% of layers run on CPU

ollama run qwen2.5:32b

tok/s

Estimated

Weights

19.00 GB

KV cache

16.00 GB

Activations

0.96 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~3045 ms (slow)

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: 28 new comfortable, 62 new tradeoff

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

Shop this upgrade↗

Upgrade to NVIDIA GeForce RTX 3090 Ti

Launch MSRP $1,999 (2022). Now sells well below its launch price on the used market. Check the current price.

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

Unlocks: 43 new comfortable

• Qwen 3 0.6B
• Qwen 3 1.7B
• Gemma 3 270M
• Mistral Small 3 24B

Shop this upgrade↗

Add a second NVIDIA RTX 2080 Ti 22GB (China-mod)

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: 71 new comfortable

• Qwen 3 0.6B
• Qwen 3 30B-A3B
• Qwen 2.5 Coder 32B Instruct
• Gemma 4 31B Dense

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