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

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)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
67 models

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

#1Hermes 3 Llama 3.1 8B
8B
hermes
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 14.7 GBHeadroom: 7.3 GBTTFT: noticeable
ollama run hermes3:8b
47
tok/s
Estimated
Weights
8.50 GB
KV cache
4.00 GB
Activations
0.43 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~761 ms (noticeable)
Model details →
#2Qwen 2.5 7B Instruct
7B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 11.2 GBTTFT: noticeable
ollama run qwen2.5:7b
54
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 →
#3Mistral 7B Instruct v0.3
7B
mistral
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 11.3 GBTTFT: noticeable
ollama run mistral:7b
83
tok/s
Estimated
Weights
5.10 GB
KV cache
3.50 GB
Activations
0.26 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~666 ms (noticeable)
Model details →
#4Llama 3.1 Nemotron Nano 8B
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 11.0 GBTTFT: noticeable
83
tok/s
Estimated
Weights
4.90 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~761 ms (noticeable)
Model details →
#5Llama 3.1 8B Instruct
8B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 11.8 GBHeadroom: 10.2 GBTTFT: noticeable
ollama run llama3.1:8b
47
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 →
#6Qwen 3 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 12.1 GBTTFT: noticeable
95
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 →
#7Qwen 2.5-VL 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 12.1 GBTTFT: noticeable
95
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 →
#8Qwen 2.5 Math 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 8.2 GBHeadroom: 13.8 GBTTFT: noticeable
95
tok/s
Estimated
Weights
4.40 GB
KV cache
1.75 GB
Activations
0.22 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~666 ms (noticeable)
Model details →
#9Qwen 2-VL 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 11.9 GBTTFT: noticeable
95
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): ~666 ms (noticeable)
Model details →
#10CodeQwen 1.5 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 12.1 GBTTFT: noticeable
95
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 →
#11Qwen 3 14B
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 4.4 GBTTFT: noticeable
ollama run qwen3:14b
47
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 →
#12Qwen 2.5 Coder 14B Instruct
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 4.4 GBTTFT: noticeable
47
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.

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
47
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 →
Dolphin 3.0 Mistral 24B
24B
dolphin
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 19.5 GBHeadroom: 2.5 GBTTFT: slow
  • • Tight VRAM fit — only 2.5 GB headroom left for context growth
ollama run dolphin-mistral:24b
28
tok/s
Estimated
Weights
14.00 GB
KV cache
3.00 GB
Activations
0.70 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~2284 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
22
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 →
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
21
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 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
21
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
21
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 →
Nemotron 3 Nano (30B-A3B)
30B
other
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 nemotron3:nano
22
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 →
Qwen3.8 27B
27B
qwen
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 36.1 GBHeadroom: 5.1 GBTTFT: slow
  • • Partial CPU offload: ~39% of layers run on CPU
ollama run qwen3.8:27b
22
tok/s
Estimated
Weights
19.80 GB
KV cache
13.50 GB
Activations
1.00 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~2570 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: 49 new comfortable, 62 new tradeoff

  • • Qwen 3 0.6B
  • • Qwen 3 1.7B
  • • Llama 3.2 3B Instruct
  • • Gemma 3 270M
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: 64 new comfortable

  • • Qwen 3 0.6B
  • • Qwen 3 1.7B
  • • Llama 3.2 3B Instruct
  • • Gemma 3 270M
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: 92 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

Even with CPU offload, needs more memory than your VRAM (22 GB) + 60% of system RAM (19 GB) combined.

—
Qwen 3.5 235B-A17B (MoE)
397B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (22 GB) + 60% of system RAM (19 GB) combined.

—
Qwen 3 235B-A22B
235B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (22 GB) + 60% of system RAM (19 GB) combined.

—
DeepSeek R1 (671B reasoning)
671B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (22 GB) + 60% of system RAM (19 GB) combined.

—
DeepSeek V4 Flash (284B MoE)
284B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (22 GB) + 60% of system RAM (19 GB) combined.

—

How to read these numbers

Measured here
Measured here - RunLocalAI ran this exact combo on owner hardware with public evidence.

Source-backed
Source-backed / community - a reproduced public source supports the speed, but it is not labeled as owner-measured.

Extrapolated
Extrapolated - predicted from a measured benchmark on similar-bandwidth hardware.

Estimated
Estimated - formula based on VRAM bandwidth and model architecture; not a benchmark row.

RunLocalAI Will-It-Run Framework →

Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.