RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Prompting kits
  • Quick answers
REF
  • All buyer guides
  • Learn local AI
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
Will it run? / NVIDIA GeForce RTX 4080 Super / chat

What can NVIDIA GeForce RTX 4080 Super run for chat?

Build: NVIDIA GeForce RTX 4080 Super + — + 32 GB RAM (windows)

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

Runs comfortably
147 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: 2.5 GBHeadroom: 13.5 GBTTFT: instant
1321
tok/s
Estimated
Weights
0.36 GB
KV cache
0.30 GB
Activations
0.03 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~29 ms (instant)
Model details →
#2TinyLlama 1.1B Chat v1.0
1.1B
llama
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 2.6 GBHeadroom: 13.4 GBTTFT: instant
720
tok/s
Estimated
Weights
0.66 GB
KV cache
0.14 GB
Activations
0.04 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~54 ms (instant)
Model details →
#3TinyLlama 1.1B Chat v0.3 AWQ
1.1B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 2.6 GBHeadroom: 13.4 GBTTFT: instant
720
tok/s
Estimated
Weights
0.66 GB
KV cache
0.14 GB
Activations
0.04 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~54 ms (instant)
Model details →
#4TinyLlama 1.1B Chat v0.3 GPTQ
1.1B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 2.6 GBHeadroom: 13.4 GBTTFT: instant
720
tok/s
Estimated
Weights
0.66 GB
KV cache
0.14 GB
Activations
0.04 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~54 ms (instant)
Model details →
#5Qwen 3 1.7B
1.7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 3.7 GBHeadroom: 12.3 GBTTFT: instant
466
tok/s
Estimated
Weights
1.03 GB
KV cache
0.85 GB
Activations
0.06 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~83 ms (instant)
Model details →
#6Gemma 2 2B Instruct
2B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.1 GBHeadroom: 11.9 GBTTFT: instant
396
tok/s
Estimated
Weights
1.21 GB
KV cache
1.00 GB
Activations
0.07 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~98 ms (instant)
Model details →
#7Kumru 2B
2.4B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.5 GBHeadroom: 11.5 GBTTFT: fast
ollama run alibayram/kumru:latest
330
tok/s
Estimated
Weights
1.45 GB
KV cache
1.20 GB
Activations
0.08 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~118 ms (fast)
Model details →
#8EXAONE 3.5 2.4B Instruct
2.4B
exaone
Quant: Q4_K_MContext: 8,192VRAM: 4.5 GBHeadroom: 11.5 GBTTFT: fast
330
tok/s
Estimated
Weights
1.45 GB
KV cache
1.20 GB
Activations
0.08 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~118 ms (fast)
Model details →
#9Llama 3.2 3B Instruct
3B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 6.7 GBHeadroom: 9.3 GBTTFT: fast
ollama run llama3.2:3b
150
tok/s
Estimated
Weights
3.19 GB
KV cache
1.50 GB
Activations
0.17 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~147 ms (fast)
Model details →
#10Qwen3 0.6B Hindi Instruct v1 GGUF
0.6B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 2.3 GBHeadroom: 13.7 GBTTFT: instant
1321
tok/s
Estimated
Weights
0.36 GB
KV cache
0.07 GB
Activations
0.02 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~29 ms (instant)
Model details →
#11Salamandra 2B Instruct
2B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.1 GBHeadroom: 11.9 GBTTFT: instant
396
tok/s
Estimated
Weights
1.21 GB
KV cache
1.00 GB
Activations
0.07 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~98 ms (instant)
Model details →
#12Falcon 3 3B Instruct
3B
falcon
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 10.8 GBTTFT: fast
264
tok/s
Estimated
Weights
1.81 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~147 ms (fast)
Model details →

Runs with tradeoffs
79 models

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

DeepSeek V2 Lite Chat
15.7B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 13.7 GBHeadroom: 2.3 GBTTFT: fast
  • • Tight VRAM fit — only 2.3 GB headroom left for context growth
330
tok/s
Estimated
Weights
9.48 GB
KV cache
1.96 GB
Activations
0.48 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~118 ms (fast)
Model details →
Gemma 2 9B Instruct
9B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 12.0 GBHeadroom: 4.0 GBTTFT: fast
  • • Tight VRAM fit — only 4.0 GB headroom left for context growth
ollama run gemma2:9b
88
tok/s
Estimated
Weights
5.43 GB
KV cache
4.50 GB
Activations
0.28 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~441 ms (fast)
Model details →
NVIDIA Nemotron Nano 9B v2 Japanese
9B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 12.0 GBHeadroom: 4.0 GBTTFT: fast
  • • Tight VRAM fit — only 4.0 GB headroom left for context growth
88
tok/s
Estimated
Weights
5.43 GB
KV cache
4.50 GB
Activations
0.28 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~441 ms (fast)
Model details →
Bielik 11B v3.0 Instruct GGUF
11B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 14.3 GBHeadroom: 1.7 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.7 GB headroom left for context growth
72
tok/s
Estimated
Weights
6.64 GB
KV cache
5.50 GB
Activations
0.34 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~539 ms (noticeable)
Model details →
Mistral Nemo 12B Instruct
12B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 15.4 GBHeadroom: 0.6 GBTTFT: noticeable
  • • Tight VRAM fit — only 0.6 GB headroom left for context growth
ollama run mistral-nemo:12b
66
tok/s
Estimated
Weights
7.25 GB
KV cache
6.00 GB
Activations
0.37 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~589 ms (noticeable)
Model details →
Gemma 3 12B
12B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 15.4 GBHeadroom: 0.6 GBTTFT: noticeable
  • • Tight VRAM fit — only 0.6 GB headroom left for context growth
ollama run gemma3:12b
66
tok/s
Estimated
Weights
7.25 GB
KV cache
6.00 GB
Activations
0.37 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~589 ms (noticeable)
Model details →
Stable LM 2 12B
12B
other
Quant: Q4_K_MContext: 4,096VRAM: 12.4 GBHeadroom: 3.6 GBTTFT: noticeable
  • • Tight VRAM fit — only 3.6 GB headroom left for context growth
66
tok/s
Estimated
Weights
7.25 GB
KV cache
3.00 GB
Activations
0.37 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~589 ms (noticeable)
Model details →
OpenThaiGPT 1.0.0 Beta 13B Chat
13B
llama
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 13.3 GBHeadroom: 2.7 GBTTFT: noticeable
  • • Tight VRAM fit — only 2.7 GB headroom left for context growth
61
tok/s
Estimated
Weights
7.85 GB
KV cache
3.25 GB
Activations
0.40 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~638 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: 25 new comfortable, 89 new tradeoff

  • • all-MiniLM-L6-v2
  • • Piper
  • • Whisper Tiny
  • • Whisper Base
Shop this upgrade↗

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

~$350

22 GB VRAM (vs your 16 GB) plus a bandwidth jump from ~736 GB/s to ~616 GB/s.

Unlocks: 53 new comfortable

  • • all-MiniLM-L6-v2
  • • Piper
  • • Whisper Tiny
  • • Whisper Base
Shop this upgrade↗

Add a second NVIDIA GeForce RTX 4080 Super

~$1099

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: 87 new comfortable

  • • all-MiniLM-L6-v2
  • • Piper
  • • Whisper Tiny
  • • Whisper Base
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 3.5 235B-A17B (MoE)
397B
qwen
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.

—
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.

—

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.