What can NVIDIA GeForce RTX 5070 Ti run for chat?

Build: RTX 5070 Ti + Ryzen 7 9700X + 32GB DDR5

Memory: 16 GB VRAM + 32 GB system RAM
Runner: llama.cpp / Ollama (CUDA)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
83 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: 13.6 GB
1256
tok/s
Estimated
Weights
0.30 GB
KV cache
0.30 GB
Activations
0.02 GB
Runtime
1.80 GB
Model details →
#2Llama 3.2 3B Instruct
3B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 6.9 GBHeadroom: 9.1 GB
ollama run llama3.2:3b
143
tok/s
Estimated
Weights
3.40 GB
KV cache
1.50 GB
Activations
0.18 GB
Runtime
1.80 GB
Model details →
#3Qwen 3 1.7B
1.7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 3.6 GBHeadroom: 12.4 GB
443
tok/s
Estimated
Weights
0.90 GB
KV cache
0.85 GB
Activations
0.05 GB
Runtime
1.80 GB
Model details →
#4TinyLlama 1.1B Chat v1.0
1.1B
llama
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 2.6 GBHeadroom: 13.4 GB
685
tok/s
Estimated
Weights
0.60 GB
KV cache
0.14 GB
Activations
0.03 GB
Runtime
1.80 GB
Model details →
#5Gemma 2 2B Instruct
2B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.0 GBHeadroom: 12.0 GB
377
tok/s
Estimated
Weights
1.10 GB
KV cache
1.00 GB
Activations
0.06 GB
Runtime
1.80 GB
Model details →
#6Kumru 2B
2.4B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.6 GBHeadroom: 11.4 GB
ollama run alibayram/kumru:latest
314
tok/s
Estimated
Weights
1.50 GB
KV cache
1.20 GB
Activations
0.08 GB
Runtime
1.80 GB
Model details →
#7Falcon 3 3B Instruct
3B
falcon
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.1 GBHeadroom: 10.9 GB
251
tok/s
Estimated
Weights
1.70 GB
KV cache
1.50 GB
Activations
0.09 GB
Runtime
1.80 GB
Model details →
#8Dolphin 3.0 Llama 3.2 3B
3B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 10.8 GB
251
tok/s
Estimated
Weights
1.80 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Model details →
#9Hermes 3 Llama 3.2 3B
3B
hermes
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 10.8 GB
251
tok/s
Estimated
Weights
1.80 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Model details →
#10Granite 3.0 2B Instruct
2B
granite
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 3.9 GBHeadroom: 12.1 GB
377
tok/s
Estimated
Weights
1.50 GB
KV cache
0.50 GB
Activations
0.08 GB
Runtime
1.80 GB
Model details →
#11Mistral Turkish v2 (brooqs)
7.2B
mistral
Quant: Q4_0Context: 8,192VRAM: 9.7 GBHeadroom: 6.3 GB
ollama run brooqs/mistral-turkish-v2:latest
112
tok/s
Estimated
Weights
4.10 GB
KV cache
3.60 GB
Activations
0.21 GB
Runtime
1.80 GB
Model details →
#12Trendyol LLM 7B Chat v0.1
7B
llama
Quant: Q4_K_MContext: 4,096VRAM: 7.6 GBHeadroom: 8.4 GB
108
tok/s
Estimated
Weights
3.90 GB
KV cache
1.75 GB
Activations
0.20 GB
Runtime
1.80 GB
Model details →

Runs with tradeoffs
46 models

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

DeepSeek V2 Lite Chat
15.7B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 12.8 GBHeadroom: 3.2 GB
  • • Tight VRAM fit — only 3.2 GB headroom left for context growth
314
tok/s
Estimated
Weights
8.60 GB
KV cache
1.96 GB
Activations
0.43 GB
Runtime
1.80 GB
Model details →
Gemma 2 9B Instruct
9B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 12.4 GBHeadroom: 3.6 GB
  • • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run gemma2:9b
84
tok/s
Estimated
Weights
5.80 GB
KV cache
4.50 GB
Activations
0.30 GB
Runtime
1.80 GB
Model details →
Mistral Nemo 12B Instruct
12B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 15.7 GBHeadroom: 0.3 GB
  • • Tight VRAM fit — only 0.3 GB headroom left for context growth
ollama run mistral-nemo:12b
63
tok/s
Estimated
Weights
7.50 GB
KV cache
6.00 GB
Activations
0.38 GB
Runtime
1.80 GB
Model details →
Gemma 3 12B
12B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 15.5 GBHeadroom: 0.5 GB
  • • Tight VRAM fit — only 0.5 GB headroom left for context growth
ollama run gemma3:12b
63
tok/s
Estimated
Weights
7.30 GB
KV cache
6.00 GB
Activations
0.37 GB
Runtime
1.80 GB
Model details →
Stable LM 2 12B
12B
other
Quant: Q4_K_MContext: 4,096VRAM: 12.4 GBHeadroom: 3.6 GB
  • • Tight VRAM fit — only 3.6 GB headroom left for context growth
63
tok/s
Estimated
Weights
7.20 GB
KV cache
3.00 GB
Activations
0.36 GB
Runtime
1.80 GB
Model details →
Qwen 3 14B
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 12.4 GBHeadroom: 3.6 GB
  • • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run qwen3:14b
54
tok/s
Estimated
Weights
8.40 GB
KV cache
1.75 GB
Activations
0.42 GB
Runtime
1.80 GB
Model details →
DeepSeek MoE 16B Base
16B
deepseek
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 15.8 GBHeadroom: 0.2 GB
  • • Tight VRAM fit — only 0.2 GB headroom left for context growth
314
tok/s
Estimated
Weights
9.50 GB
KV cache
4.00 GB
Activations
0.48 GB
Runtime
1.80 GB
Model details →
GLM-4 9B
9B
glm
Quant: Q4_K_MContext: 8,192VRAM: 12.1 GBHeadroom: 3.9 GB
  • • Tight VRAM fit — only 3.9 GB headroom left for context growth
84
tok/s
Estimated
Weights
5.50 GB
KV cache
4.50 GB
Activations
0.28 GB
Runtime
1.80 GB
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: 5 new comfortable, 57 new tradeoff

  • • Gemma 3 270M
  • • SmolLM2 135M Instruct
  • • SmolLM2 360M Instruct
  • • VBART Large (Turkish Summarization)
Shop this upgrade↗

Upgrade to NVIDIA RTX 2080 Ti 22GB (China-mod)

Check the current price

22 GB VRAM (vs your 16 GB) plus a bandwidth jump from ~? GB/s to ~616 GB/s.

Unlocks: 24 new comfortable

  • • Qwen 3 14B
  • • Gemma 3 270M
  • • Phi-4 14B
  • • Phi-4 Reasoning 14B

Add a second NVIDIA GeForce RTX 5070 Ti

Launch MSRP $749 (2025). 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: 45 new comfortable

  • • Qwen 3 30B-A3B
  • • Qwen 2.5 Coder 32B Instruct
  • • Qwen 3 32B
  • • Gemma 4 31B Dense
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 (16 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 (16 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 (16 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 (16 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 (16 GB) + 60% of system RAM (19 GB) combined.

—
Cloud GPU rental

Not enough VRAM for these models? Rent a GPU by the hour

The models above need more memory than 16 GB VRAM + 32 GB system RAM. You can rent a GPU with enough VRAM by the hour to run one of them, or to test it before you buy hardware. For daily use, owning a card usually costs less over time.

RunPod

billed per GPU-hour

Hourly GPU pods, in community-cloud and secure-cloud tiers.

The two tiers run on different hosts and terms. Check which tier a pod is on before a long job.

Rent on RunPod

Vast.ai

billed per GPU-hour

Marketplace of host-listed GPUs; price and reliability vary by host.

Host quality varies. Filter for verified hosts and check the host's reliability before a long run.

Rent on Vast.ai

Referral links: RunLocalAI may earn a commission or account credits if you sign up and rent, at no extra cost to you. Hourly rates and which GPUs are listed change all the time, so check the provider's page before you start. Editorial opinions are independent of the referral relationship; see how we make money.

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.