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 / reasoning

What can NVIDIA GeForce RTX 4080 Super run for reasoning?

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
74 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: 10.9 GBHeadroom: 5.1 GBTTFT: fast
99
tok/s
Estimated
Weights
4.83 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~392 ms (fast)
Model details →
#2RefinedNeuro RN TR R1
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.9 GBHeadroom: 5.1 GBTTFT: fast
ollama run RefinedNeuro/RN_TR_R1:latest
99
tok/s
Estimated
Weights
4.83 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~392 ms (fast)
Model details →
#3DeepSeek R1 Distill Llama 8B
8B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.9 GBHeadroom: 5.1 GBTTFT: fast
99
tok/s
Estimated
Weights
4.83 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~392 ms (fast)
Model details →
#4InternLM 2.5 7B Chat
7B
internlm
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 6.3 GBTTFT: fast
113
tok/s
Estimated
Weights
4.23 GB
KV cache
3.50 GB
Activations
0.22 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Model details →
#5Qwen 2.5 Math 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 8.0 GBHeadroom: 8.0 GBTTFT: fast
113
tok/s
Estimated
Weights
4.23 GB
KV cache
1.75 GB
Activations
0.22 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Model details →
#6Qwen 3 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 6.3 GBTTFT: fast
113
tok/s
Estimated
Weights
4.23 GB
KV cache
3.50 GB
Activations
0.22 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Model details →
#7EXAONE Deep 7.8B
7.8B
other
Quant: Q4_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 5.3 GBTTFT: fast
102
tok/s
Estimated
Weights
4.71 GB
KV cache
3.90 GB
Activations
0.24 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~383 ms (fast)
Model details →
#8RefinedNeuro RN TR R2
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.9 GBHeadroom: 5.1 GBTTFT: fast
ollama run RefinedNeuro/RN_TR_R2:latest
99
tok/s
Estimated
Weights
4.83 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~392 ms (fast)
Model details →
#9Mistral Turkish v2 (brooqs)
7.2B
mistral
Quant: Q4_0Context: 8,192VRAM: 9.7 GBHeadroom: 6.3 GBTTFT: fast
ollama run brooqs/mistral-turkish-v2:latest
118
tok/s
Estimated
Weights
4.05 GB
KV cache
3.60 GB
Activations
0.21 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~353 ms (fast)
Model details →
#10Trendyol LLM 7B Chat v0.1
7B
llama
Quant: Q4_K_MContext: 4,096VRAM: 8.0 GBHeadroom: 8.0 GBTTFT: fast
113
tok/s
Estimated
Weights
4.23 GB
KV cache
1.75 GB
Activations
0.22 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Model details →
#11Mistral 7B Instruct v0.2
7B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 6.3 GBTTFT: fast
113
tok/s
Estimated
Weights
4.23 GB
KV cache
3.50 GB
Activations
0.22 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Model details →
#12Salamandra 7B Instruct
7B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 6.3 GBTTFT: fast
113
tok/s
Estimated
Weights
4.23 GB
KV cache
3.50 GB
Activations
0.22 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Model details →

Runs with tradeoffs
79 models

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

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 →
DeepSeek R1 Distill Qwen 7B
7B
deepseek
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 13.1 GBHeadroom: 2.9 GBTTFT: fast
  • • Tight VRAM fit — only 2.9 GB headroom left for context growth
ollama run deepseek-r1:7b
64
tok/s
Estimated
Weights
7.44 GB
KV cache
3.50 GB
Activations
0.38 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Model details →
Phi-4 Reasoning 14B
14B
phi
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 12.4 GBHeadroom: 3.6 GBTTFT: noticeable
  • • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run phi4-reasoning:14b
57
tok/s
Estimated
Weights
8.45 GB
KV cache
1.75 GB
Activations
0.42 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~687 ms (noticeable)
Model details →
DeepSeek R1 Distill Qwen 14B
14B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 12.4 GBHeadroom: 3.6 GBTTFT: noticeable
  • • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run deepseek-r1:14b
57
tok/s
Estimated
Weights
8.45 GB
KV cache
1.75 GB
Activations
0.42 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~687 ms (noticeable)
Model details →
DeepSeek V3 Lite (16B MoE)
16B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 13.9 GBHeadroom: 2.1 GBTTFT: fast
  • • Tight VRAM fit — only 2.1 GB headroom left for context growth
330
tok/s
Estimated
Weights
9.66 GB
KV cache
2.00 GB
Activations
0.49 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~118 ms (fast)
Model details →
DeepSeek R1 Distill Mistral 24B
24B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 29.0 GBHeadroom: 6.2 GBTTFT: noticeable
  • • Partial CPU offload: ~45% of layers run on CPU
33
tok/s
Estimated
Weights
14.49 GB
KV cache
12.00 GB
Activations
0.73 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1177 ms (noticeable)
Model details →
Omni 31B Turkish Reasoning
31B
other
Quant: Q4_K_MContext: 2,048VRAM: 25.3 GBHeadroom: 9.9 GBTTFT: noticeable
  • • Partial CPU offload: ~37% of layers run on CPU
26
tok/s
Estimated
Weights
18.72 GB
KV cache
3.88 GB
Activations
0.94 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1520 ms (noticeable)
Model details →
DeepSeek R1 Distill Qwen 32B
32B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 26.1 GBHeadroom: 9.1 GBTTFT: noticeable
  • • Partial CPU offload: ~39% of layers run on CPU
ollama run deepseek-r1:32b
25
tok/s
Estimated
Weights
19.32 GB
KV cache
4.00 GB
Activations
0.97 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1569 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: 98 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: 126 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: 160 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.