What can NVIDIA GeForce RTX 4090 run for agents?

Build: NVIDIA GeForce RTX 4090 + — + 32 GB RAM (windows)

Memory: 24 GB VRAM + 32 GB system RAM
Runner: llama.cpp / Ollama (CUDA)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
120 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: 9.3 GBTTFT: fast
ollama run hermes3:8b
77
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): ~248 ms (fast)
Model details →
#2Qwen 2.5 14B Instruct
14B
qwen
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 19.8 GBHeadroom: 4.2 GBTTFT: fast
ollama run qwen2.5:14b
68
tok/s
Estimated
Weights
10.50 GB
KV cache
7.00 GB
Activations
0.53 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~434 ms (fast)
Model details →
#3Dolphin 3.0 Mistral 24B
24B
dolphin
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 19.5 GBHeadroom: 4.5 GBTTFT: noticeable
ollama run dolphin-mistral:24b
45
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): ~744 ms (noticeable)
Model details →
#4Qwen 2.5 7B Instruct
7B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 13.2 GBTTFT: fast
ollama run qwen2.5:7b
88
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): ~217 ms (fast)
Model details →
#5Ornith 1.0 9B
9B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 12.2 GBHeadroom: 11.8 GBTTFT: fast
ollama run ornith:9b
121
tok/s
Estimated
Weights
5.60 GB
KV cache
4.50 GB
Activations
0.29 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~279 ms (fast)
Model details →
#6Llama 3.1 Nemotron Nano 8B
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 13.0 GBTTFT: fast
136
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): ~248 ms (fast)
Model details →
#7Mistral 7B Instruct v0.3
7B
mistral
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 13.3 GBTTFT: fast
ollama run mistral:7b
136
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): ~217 ms (fast)
Model details →
#8Mellum2 12B-A2.5B
12.15B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 16.3 GBHeadroom: 7.7 GBTTFT: fast
ollama run hf.co/JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M
89
tok/s
Estimated
Weights
8.00 GB
KV cache
6.08 GB
Activations
0.41 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~377 ms (fast)
Model details →
#9Mistral Small 3 24B
24B
mistral
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 19.5 GBHeadroom: 4.5 GBTTFT: noticeable
ollama run mistral-small:24b
45
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): ~744 ms (noticeable)
Model details →
#10Llama 3.1 8B Instruct
8B
llama
Commercial OK
Quant: FP16Context: 8,192VRAM: 19.8 GBHeadroom: 4.2 GBTTFT: fast
ollama run llama3.1:8b
41
tok/s
Estimated
Weights
16.10 GB
KV cache
1.07 GB
Activations
0.81 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~248 ms (fast)
Model details →
#11Dolphin 3.0 8B
8B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.1 GBHeadroom: 12.9 GBTTFT: fast
ollama run dolphin3:8b
136
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): ~248 ms (fast)
Model details →
#12Qwen 3 14B
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 6.4 GBTTFT: fast
ollama run qwen3:14b
78
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): ~434 ms (fast)
Model details →

Runs with tradeoffs
56 models

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

Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 35.7 GBHeadroom: 7.5 GBTTFT: noticeable
  • • Partial CPU offload: ~33% of layers run on CPU
ollama run qwen3:30b
36
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): ~930 ms (noticeable)
Model details →
Qwen3 Coder 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 36.8 GBHeadroom: 6.4 GBTTFT: noticeable
  • • Partial CPU offload: ~35% of layers run on CPU
ollama run qwen3-coder:30b
36
tok/s
Estimated
Weights
19.00 GB
KV cache
15.00 GB
Activations
0.96 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~930 ms (noticeable)
Model details →
Qwen 2.5 Coder 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 23.9 GBHeadroom: 0.1 GBTTFT: noticeable
  • • Tight VRAM fit — only 0.1 GB headroom left for context growth
ollama run qwen2.5-coder:32b
34
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): ~992 ms (noticeable)
Model details →
Qwen 3 32B
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 37.8 GBHeadroom: 5.4 GBTTFT: noticeable
  • • Partial CPU offload: ~36% of layers run on CPU
ollama run qwen3:32b
34
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): ~992 ms (noticeable)
Model details →
Qwen 2.5 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 37.8 GBHeadroom: 5.4 GBTTFT: noticeable
  • • Partial CPU offload: ~36% of layers run on CPU
ollama run qwen2.5:32b
34
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): ~992 ms (noticeable)
Model details →
Nemotron 3 Nano (30B-A3B)
30B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 35.7 GBHeadroom: 7.5 GBTTFT: noticeable
  • • Partial CPU offload: ~33% of layers run on CPU
ollama run nemotron3:nano
36
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): ~930 ms (noticeable)
Model details →
North Mini Code 1.0
30B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 36.8 GBHeadroom: 6.4 GBTTFT: noticeable
  • • Partial CPU offload: ~35% of layers run on CPU
ollama run north-mini-code-1.0
36
tok/s
Estimated
Weights
19.00 GB
KV cache
15.00 GB
Activations
0.96 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~930 ms (noticeable)
Model details →
GLM-4.7-Flash
31B
glm
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 37.3 GBHeadroom: 5.9 GBTTFT: noticeable
  • • Partial CPU offload: ~36% of layers run on CPU
ollama run glm-4.7-flash
35
tok/s
Estimated
Weights
19.00 GB
KV cache
15.50 GB
Activations
0.96 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~961 ms (noticeable)
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: 64 new comfortable, 73 new tradeoff

  • • Qwen 3 0.6B
  • • Llama 3.2 3B Instruct
  • • Qwen 3 1.7B
  • • Gemma 3 270M
Shop this upgrade↗

Upgrade to NVIDIA RTX PRO 4500 Blackwell

see current pricing

32 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~1008 GB/s to ~896 GB/s.

Unlocks: 103 new comfortable

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

Add a second NVIDIA GeForce RTX 4090

~$1899

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: 116 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

Even with CPU offload, needs more memory than your VRAM (24 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 (24 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 (24 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 (24 GB) + 60% of system RAM (19 GB) combined.

—
Llama 4 Scout
109B
llama
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 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.