What can NVIDIA RTX A5000 run for chat?

Build: NVIDIA RTX A5000 + — + 32 GB RAM (windows)

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

Runs comfortably
125 models

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

#1Qwen 3 0.6B
0.6B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.4 GBHeadroom: 21.6 GB
2692
tok/s
Estimated
Weights
0.30 GB
KV cache
0.30 GB
Activations
0.02 GB
Runtime
1.80 GB
#2Qwen 3 1.7B
1.7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 3.6 GBHeadroom: 20.4 GB
950
tok/s
Estimated
Weights
0.90 GB
KV cache
0.85 GB
Activations
0.05 GB
Runtime
1.80 GB
#3Llama 3.2 3B Instruct
3B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 6.9 GBHeadroom: 17.1 GB
ollama run llama3.2:3b
306
tok/s
Estimated
Weights
3.40 GB
KV cache
1.50 GB
Activations
0.18 GB
Runtime
1.80 GB
#4Gemma 3 12B
12B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 15.5 GBHeadroom: 8.5 GB
ollama run gemma3:12b
135
tok/s
Estimated
Weights
7.30 GB
KV cache
6.00 GB
Activations
0.37 GB
Runtime
1.80 GB
#5TinyLlama 1.1B Chat v1.0
1.1B
llama
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 2.6 GBHeadroom: 21.4 GB
1468
tok/s
Estimated
Weights
0.60 GB
KV cache
0.14 GB
Activations
0.03 GB
Runtime
1.80 GB
#6Gemma 2 2B Instruct
2B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.0 GBHeadroom: 20.0 GB
807
tok/s
Estimated
Weights
1.10 GB
KV cache
1.00 GB
Activations
0.06 GB
Runtime
1.80 GB
#7Mistral 7B Instruct v0.3
7B
mistral
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 13.3 GB
ollama run mistral:7b
203
tok/s
Estimated
Weights
5.10 GB
KV cache
3.50 GB
Activations
0.26 GB
Runtime
1.80 GB
#8DeepSeek V2 Lite Chat
15.7B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 18.7 GBHeadroom: 5.3 GB
673
tok/s
Estimated
Weights
8.60 GB
KV cache
7.85 GB
Activations
0.44 GB
Runtime
1.80 GB
Quant: Q4_K_MContext: 4,096VRAM: 7.6 GBHeadroom: 16.4 GB
231
tok/s
Estimated
Weights
3.90 GB
KV cache
1.75 GB
Activations
0.20 GB
Runtime
1.80 GB
#10Kumru 2B
2.4B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.6 GBHeadroom: 19.4 GB
ollama run alibayram/kumru:latest
673
tok/s
Estimated
Weights
1.50 GB
KV cache
1.20 GB
Activations
0.08 GB
Runtime
1.80 GB
#11Turkcell LLM 7B v1
7.4B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 13.8 GB
ollama run RefinedNeuro/Turkcell-LLM-7b-v1:latest
218
tok/s
Estimated
Weights
4.50 GB
KV cache
3.70 GB
Activations
0.23 GB
Runtime
1.80 GB
Quant: Q4_0Context: 8,192VRAM: 9.7 GBHeadroom: 14.3 GB
ollama run brooqs/mistral-turkish-v2:latest
241
tok/s
Estimated
Weights
4.10 GB
KV cache
3.60 GB
Activations
0.21 GB
Runtime
1.80 GB

Runs with tradeoffs
32 models

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

Gemma 4 26B MoE
26B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 21.9 GBHeadroom: 2.1 GB
  • • Tight VRAM fit — only 2.1 GB headroom left for context growth
ollama run gemma4:26b-moe
62
tok/s
Estimated
Weights
16.00 GB
KV cache
3.25 GB
Activations
0.80 GB
Runtime
1.80 GB
Gemma 3 27B
27B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 22.0 GBHeadroom: 2.0 GB
  • • Tight VRAM fit — only 2.0 GB headroom left for context growth
ollama run gemma3:27b
60
tok/s
Estimated
Weights
16.00 GB
KV cache
3.38 GB
Activations
0.80 GB
Runtime
1.80 GB
Gemma 4 31B Dense
31B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 36.2 GBHeadroom: 7.0 GB
  • • Partial CPU offload: ~34% of layers run on CPU
ollama run gemma4:31b
52
tok/s
Estimated
Weights
18.00 GB
KV cache
15.50 GB
Activations
0.91 GB
Runtime
1.80 GB
OLMo 2 32B
32B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 37.8 GBHeadroom: 5.4 GB
  • • Partial CPU offload: ~36% of layers run on CPU
50
tok/s
Estimated
Weights
19.00 GB
KV cache
16.00 GB
Activations
0.96 GB
Runtime
1.80 GB
Yi 1.5 34B
34B
yi
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 39.8 GBHeadroom: 3.4 GB
  • • Partial CPU offload: ~40% of layers run on CPU
ollama run yi:34b
47
tok/s
Estimated
Weights
20.00 GB
KV cache
17.00 GB
Activations
1.01 GB
Runtime
1.80 GB
Mixtral 8x7B Instruct
47B
mixtral
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 37.1 GBHeadroom: 6.1 GB
  • • Partial CPU offload: ~35% of layers run on CPU
ollama run mixtral:8x7b
34
tok/s
Estimated
Weights
28.00 GB
KV cache
5.88 GB
Activations
1.40 GB
Runtime
1.80 GB
Jamba 1.5 Mini
52B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 39.8 GBHeadroom: 3.4 GB
  • • Partial CPU offload: ~40% of layers run on CPU
135
tok/s
Estimated
Weights
30.00 GB
KV cache
6.50 GB
Activations
1.50 GB
Runtime
1.80 GB
Llama 3.2 11B Vision Instruct
11B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 20.4 GBHeadroom: 3.6 GB
  • • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run llama3.2-vision:11b
83
tok/s
Estimated
Weights
12.50 GB
KV cache
5.50 GB
Activations
0.63 GB
Runtime
1.80 GB

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: 5 new comfortable, 48 new tradeoff

  • • Gemma 3 270M
  • • SmolLM2 135M Instruct
  • • SmolLM2 360M Instruct
  • • VBART Large (Turkish Summarization)

Upgrade to NVIDIA GeForce RTX 5090

Launch MSRP $1,999 (2025). Check the current price.

32 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~? GB/s to ~1792 GB/s.

Unlocks: 29 new comfortable

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

Add a second NVIDIA RTX A5000

Launch MSRP $2,500 (2021). 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: 37 new comfortable

  • • Qwen 3 30B-A3B
  • • Qwen 2.5 Coder 32B Instruct
  • • Qwen 3 32B
  • • 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 (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.

—
DeepSeek V4 Flash (284B MoE)
284B
deepseek
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.