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 4090 / coding

What can NVIDIA GeForce RTX 4090 run for coding?

Build: NVIDIA GeForce RTX 4090 + — + 32 GB RAM (windows)

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

Runs comfortably
135 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: 14.3 GBTTFT: fast
ollama run codegemma:7b
155
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): ~217 ms (fast)
Model details →
#2DeepSeek Coder V2 Lite (16B)
16B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 20.0 GBHeadroom: 4.0 GBTTFT: fast
ollama run deepseek-coder-v2:16b
68
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): ~496 ms (fast)
Model details →
#3Codestral 22B
22B
mistral
Quant: Q4_K_MContext: 2,048VRAM: 18.5 GBHeadroom: 5.5 GBTTFT: noticeable
ollama run codestral:22b
49
tok/s
Estimated
Weights
13.28 GB
KV cache
2.75 GB
Activations
0.67 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~682 ms (noticeable)
Model details →
#4Qwen 3 14B
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.7 GBHeadroom: 6.3 GBTTFT: fast
ollama run qwen3:14b
78
tok/s
Estimated
Weights
8.45 GB
KV cache
7.00 GB
Activations
0.43 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~434 ms (fast)
Model details →
#5Qwen 2.5 14B Instruct
14B
qwen
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 18.9 GBHeadroom: 5.1 GBTTFT: fast
ollama run qwen2.5:14b
68
tok/s
Estimated
Weights
9.63 GB
KV cache
7.00 GB
Activations
0.49 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~434 ms (fast)
Model details →
#6Qwen 2.5 7B Instruct
7B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 10.1 GBHeadroom: 13.9 GBTTFT: fast
ollama run qwen2.5:7b
88
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): ~217 ms (fast)
Model details →
#7Qwen 3 8B
8B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 14.7 GBHeadroom: 9.3 GBTTFT: fast
ollama run qwen3:8b
77
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): ~248 ms (fast)
Model details →
#8Llama 3.1 8B Instruct
8B
llama
Commercial OK
Quant: FP16Context: 8,192VRAM: 19.7 GBHeadroom: 4.3 GBTTFT: fast
ollama run llama3.1:8b
41
tok/s
Estimated
Weights
16.00 GB
KV cache
1.07 GB
Activations
0.81 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~248 ms (fast)
Model details →
#9Gervásio 8B PTPT
8B
llama
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 8.9 GBHeadroom: 15.1 GBTTFT: fast
136
tok/s
Estimated
Weights
4.83 GB
KV cache
2.00 GB
Activations
0.25 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~248 ms (fast)
Model details →
#10StarCoder 2 7B
7B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 14.3 GBTTFT: fast
155
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): ~217 ms (fast)
Model details →
#11StarCoder 2 3B
3B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 18.8 GBTTFT: instant
362
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): ~93 ms (instant)
Model details →
#12Yi Coder 9B
9B
yi
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 12.0 GBHeadroom: 12.0 GBTTFT: fast
121
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): ~279 ms (fast)
Model details →

Runs with tradeoffs
52 models

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

Qwen 2.5 Coder 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 22.6 GBHeadroom: 1.4 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.4 GB headroom left for context growth
ollama run qwen2.5-coder:32b
34
tok/s
Estimated
Weights
19.32 GB
KV cache
0.54 GB
Activations
0.97 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~992 ms (noticeable)
Model details →
Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 35.8 GBHeadroom: 7.4 GBTTFT: noticeable
  • • Partial CPU offload: ~33% of layers run on CPU
ollama run qwen3:30b
36
tok/s
Estimated
Weights
18.11 GB
KV cache
15.00 GB
Activations
0.91 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~930 ms (noticeable)
Model details →
Gemma 4 31B Dense
31B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 37.0 GBHeadroom: 6.2 GBTTFT: noticeable
  • • Partial CPU offload: ~35% of layers run on CPU
ollama run gemma4:31b
35
tok/s
Estimated
Weights
18.72 GB
KV cache
15.50 GB
Activations
0.94 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~961 ms (noticeable)
Model details →
Qwen 2.5 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 38.1 GBHeadroom: 5.1 GBTTFT: noticeable
  • • Partial CPU offload: ~37% of layers run on CPU
ollama run qwen2.5:32b
34
tok/s
Estimated
Weights
19.32 GB
KV cache
16.00 GB
Activations
0.97 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~992 ms (noticeable)
Model details →
Qwen 3 32B
32B
qwen
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 40.9 GBHeadroom: 2.3 GBTTFT: noticeable
  • • Partial CPU offload: ~41% of layers run on CPU
ollama run qwen3:32b
30
tok/s
Estimated
Weights
22.00 GB
KV cache
16.00 GB
Activations
1.11 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~992 ms (noticeable)
Model details →
Mistral Small 3 24B
24B
mistral
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 20.0 GBHeadroom: 4.0 GBTTFT: noticeable
  • • Tight VRAM fit — only 4.0 GB headroom left for context growth
ollama run mistral-small:24b
45
tok/s
Estimated
Weights
14.49 GB
KV cache
3.00 GB
Activations
0.73 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~744 ms (noticeable)
Model details →
Qwen 3 Coder 32B
32B
qwen
Commercial OK
Quant: AWQ-INT4Context: 2,048VRAM: 39.4 GBHeadroom: 3.8 GBTTFT: noticeable
  • • Partial CPU offload: ~39% of layers run on CPU
20
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): ~992 ms (noticeable)
Model details →
DeepSeek Coder V3
33B
deepseek
Commercial OK
Quant: AWQ-INT4Context: 2,048VRAM: 40.6 GBHeadroom: 2.6 GBTTFT: noticeable
  • • Partial CPU offload: ~41% of layers run on CPU
20
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): ~1023 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, 65 new tradeoff

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

Upgrade to NVIDIA RTX PRO 4500 Blackwell

see current pricing

32 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~1008 GB/s to ~896 GB/s.

Unlocks: 99 new comfortable

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

Add a second NVIDIA GeForce RTX 4090

~$1899

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: 123 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 (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.