What can NVIDIA GeForce RTX 4090 run for reasoning?

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 reasoning use case + predicted speed. Click a row for VRAM breakdown.

#1Llama 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 →
#2NVIDIA Nemotron Nano 9B v2 Japanese
9B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.6 GBHeadroom: 12.4 GBTTFT: fast
121
tok/s
Estimated
Weights
5.00 GB
KV cache
4.50 GB
Activations
0.26 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~279 ms (fast)
Model details →
#3RefinedNeuro RN TR R1
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 13.0 GBTTFT: fast
ollama run RefinedNeuro/RN_TR_R1:latest
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 →
#4DeepSeek R1 Distill Llama 8B
8B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 13.3 GBTTFT: fast
136
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): ~248 ms (fast)
Model details →
#5DeepSeek R1 Distill Qwen 7B
7B
deepseek
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 13.8 GBHeadroom: 10.2 GBTTFT: fast
ollama run deepseek-r1:7b
88
tok/s
Estimated
Weights
8.10 GB
KV cache
3.50 GB
Activations
0.41 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~217 ms (fast)
Model details →
#6Phi-4 Reasoning 14B
14B
phi
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 6.4 GBTTFT: fast
ollama run phi4-reasoning: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 →
#7DeepSeek R1 Distill Qwen 14B
14B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 6.4 GBTTFT: fast
ollama run deepseek-r1:14b
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 →
#8DeepSeek V3 Lite (16B MoE)
16B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 19.8 GBHeadroom: 4.2 GBTTFT: instant
452
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): ~74 ms (instant)
Model details →
#9DeepSeek R1 Distill Mistral 24B
24B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 19.5 GBHeadroom: 4.5 GBTTFT: noticeable
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 →
#10Phi-4 14B
14B
phi
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 6.4 GBTTFT: fast
ollama run phi4:14b
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 →
#11EXAONE Deep 7.8B
7.8B
other
Quant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 13.8 GBTTFT: fast
139
tok/s
Estimated
Weights
4.30 GB
KV cache
3.90 GB
Activations
0.22 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~242 ms (fast)
Model details →
#12RefinedNeuro RN TR R2
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 13.0 GBTTFT: fast
ollama run RefinedNeuro/RN_TR_R2:latest
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 →

Runs with tradeoffs
56 models

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

Omni 31B Turkish Reasoning
31B
other
Quant: Q4_K_MContext: 2,048VRAM: 23.6 GBHeadroom: 0.4 GBTTFT: noticeable
  • • Tight VRAM fit — only 0.4 GB headroom left for context growth
35
tok/s
Estimated
Weights
17.10 GB
KV cache
3.88 GB
Activations
0.86 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~961 ms (noticeable)
Model details →
DeepSeek R1 Distill Qwen 32B
32B
deepseek
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 deepseek-r1:32b
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 →
QwQ 32B Preview
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 qwq: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 →
EXAONE 4.0.1 32B
32B
exaone
Quant: Q4_K_MContext: 8,192VRAM: 36.3 GBHeadroom: 6.9 GBTTFT: noticeable
  • • Partial CPU offload: ~34% of layers run on CPU
34
tok/s
Estimated
Weights
17.60 GB
KV cache
16.00 GB
Activations
0.89 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~992 ms (noticeable)
Model details →
Qwen3 Swallow 32B RL v0.2
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 36.3 GBHeadroom: 6.9 GBTTFT: noticeable
  • • Partial CPU offload: ~34% of layers run on CPU
34
tok/s
Estimated
Weights
17.60 GB
KV cache
16.00 GB
Activations
0.89 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~992 ms (noticeable)
Model details →
DeepSeek R1 Distill Qwen 3 32B
32B
deepseek
Commercial OK
Quant: AWQ-INT4Context: 8,192VRAM: 37.8 GBHeadroom: 5.4 GBTTFT: noticeable
  • • Partial CPU offload: ~36% of layers run on CPU
20
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 →
Sarvam M
24B
mistral
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 21.7 GBHeadroom: 2.3 GBTTFT: noticeable
  • • Tight VRAM fit — only 2.3 GB headroom left for context growth
45
tok/s
Estimated
Weights
13.20 GB
KV cache
6.00 GB
Activations
0.66 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~744 ms (noticeable)
Model details →
Magistral 32B
32B
mistral
Quant: AWQ-INT4Context: 8,192VRAM: 37.8 GBHeadroom: 5.4 GBTTFT: noticeable
  • • Partial CPU offload: ~36% of layers run on CPU
20
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 →

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.