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 5090 / coding

What can NVIDIA GeForce RTX 5090 run for coding?

Build: NVIDIA GeForce RTX 5090 + — + 32 GB RAM (windows)

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

Runs comfortably
161 models

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

#1CodeGemma 7B
7B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 22.3 GBTTFT: fast
ollama run codegemma:7b
276
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): ~143 ms (fast)
Model details →
#2DeepSeek Coder V2 Lite (16B)
16B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 20.0 GBHeadroom: 12.0 GBTTFT: fast
ollama run deepseek-coder-v2:16b
121
tok/s
Estimated
Weights
9.66 GB
KV cache
8.00 GB
Activations
0.49 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~328 ms (fast)
Model details →
#3Codestral 22B
22B
mistral
Quant: Q4_K_MContext: 8,192VRAM: 26.8 GBHeadroom: 5.2 GBTTFT: fast
ollama run codestral:22b
88
tok/s
Estimated
Weights
13.28 GB
KV cache
11.00 GB
Activations
0.67 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~451 ms (fast)
Model details →
#4Qwen 2.5 Coder 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 24.2 GBHeadroom: 7.8 GBTTFT: noticeable
ollama run qwen2.5-coder:32b
60
tok/s
Estimated
Weights
19.32 GB
KV cache
2.15 GB
Activations
0.97 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~655 ms (noticeable)
Model details →
#5Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 24.6 GBHeadroom: 7.4 GBTTFT: noticeable
ollama run qwen3:30b
64
tok/s
Estimated
Weights
18.11 GB
KV cache
3.75 GB
Activations
0.91 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~614 ms (noticeable)
Model details →
#6Gemma 4 31B Dense
31B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 25.3 GBHeadroom: 6.7 GBTTFT: noticeable
ollama run gemma4:31b
62
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): ~635 ms (noticeable)
Model details →
#7Qwen 3 32B
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 26.1 GBHeadroom: 5.9 GBTTFT: noticeable
ollama run qwen3:32b
60
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): ~655 ms (noticeable)
Model details →
#8Qwen 2.5 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 26.1 GBHeadroom: 5.9 GBTTFT: noticeable
ollama run qwen2.5:32b
60
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): ~655 ms (noticeable)
Model details →
#9Qwen 2.5 7B Instruct
7B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 10.1 GBHeadroom: 21.9 GBTTFT: fast
ollama run qwen2.5:7b
157
tok/s
Estimated
Weights
7.44 GB
KV cache
0.47 GB
Activations
0.38 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~143 ms (fast)
Model details →
#10Qwen 3 8B
8B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 14.7 GBHeadroom: 17.3 GBTTFT: fast
ollama run qwen3:8b
137
tok/s
Estimated
Weights
8.50 GB
KV cache
4.00 GB
Activations
0.43 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~164 ms (fast)
Model details →
#11Qwen 3 14B
14B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 24.4 GBHeadroom: 7.6 GBTTFT: fast
ollama run qwen3:14b
78
tok/s
Estimated
Weights
14.88 GB
KV cache
7.00 GB
Activations
0.75 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~287 ms (fast)
Model details →
#12Qwen 2.5 14B Instruct
14B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 24.4 GBHeadroom: 7.6 GBTTFT: fast
ollama run qwen2.5:14b
78
tok/s
Estimated
Weights
14.88 GB
KV cache
7.00 GB
Activations
0.75 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~287 ms (fast)
Model details →

Runs with tradeoffs
27 models

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

Mistral Small 3 24B
24B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 29.0 GBHeadroom: 3.0 GBTTFT: fast
  • • Tight VRAM fit — only 3.0 GB headroom left for context growth
ollama run mistral-small:24b
80
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): ~492 ms (fast)
Model details →
Llama 3.3 70B Instruct
70B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 48.9 GBHeadroom: 2.3 GBTTFT: noticeable
  • • Partial CPU offload: ~35% of layers run on CPU
ollama run llama3.3:70b
28
tok/s
Estimated
Weights
42.26 GB
KV cache
2.68 GB
Activations
2.12 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1434 ms (noticeable)
Model details →
Qwen 3 Coder 32B
32B
qwen
Commercial OK
Quant: AWQ-INT4Context: 2,048VRAM: 39.4 GBHeadroom: 11.8 GBTTFT: noticeable
  • • Partial CPU offload: ~19% of layers run on CPU
36
tok/s
Estimated
Weights
32.00 GB
KV cache
4.00 GB
Activations
1.60 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~655 ms (noticeable)
Model details →
DeepSeek Coder V3
33B
deepseek
Commercial OK
Quant: AWQ-INT4Context: 2,048VRAM: 40.6 GBHeadroom: 10.6 GBTTFT: noticeable
  • • Partial CPU offload: ~21% of layers run on CPU
35
tok/s
Estimated
Weights
33.00 GB
KV cache
4.13 GB
Activations
1.65 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~676 ms (noticeable)
Model details →
Jamba 1.5 Mini
52B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 41.3 GBHeadroom: 9.9 GBTTFT: fast
  • • Partial CPU offload: ~22% of layers run on CPU
161
tok/s
Estimated
Weights
31.39 GB
KV cache
6.50 GB
Activations
1.57 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~246 ms (fast)
Model details →
Sarvam 30B
30B
other
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 28.3 GBHeadroom: 3.7 GBTTFT: noticeable
  • • Tight VRAM fit — only 3.7 GB headroom left for context growth
64
tok/s
Estimated
Weights
18.11 GB
KV cache
7.50 GB
Activations
0.91 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~614 ms (noticeable)
Model details →
Pollux Judge 32B
32B
other
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 30.1 GBHeadroom: 1.9 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.9 GB headroom left for context growth
60
tok/s
Estimated
Weights
19.32 GB
KV cache
8.00 GB
Activations
0.97 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~655 ms (noticeable)
Model details →
Mihenk LLM v2 35B (Turkish Financial)
35B
other
Quant: Q4_K_MContext: 2,048VRAM: 28.4 GBHeadroom: 3.6 GBTTFT: noticeable
  • • Tight VRAM fit — only 3.6 GB headroom left for context growth
55
tok/s
Estimated
Weights
21.13 GB
KV cache
4.38 GB
Activations
1.06 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~717 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: 73 new comfortable, 40 new tradeoff

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

Upgrade to NVIDIA A100 40GB

see current pricing

40 GB VRAM (vs your 32 GB) plus a bandwidth jump from ~1792 GB/s to ~1555 GB/s.

Unlocks: 90 new comfortable

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

Add a second NVIDIA GeForce RTX 5090

~$2499

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: 110 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 (32 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 (32 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 (32 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 (32 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 (32 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.