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 / long context

What can NVIDIA GeForce RTX 4090 run for long context?

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 long context use case + predicted speed. Click a row for VRAM breakdown.

#1Phi-3.5 Mini Instruct
3.8B
phi
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 7.9 GBHeadroom: 16.1 GBTTFT: fast
ollama run phi3.5:3.8b
162
tok/s
Estimated
Weights
4.04 GB
KV cache
1.90 GB
Activations
0.21 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~118 ms (fast)
Model details →
#2Gemma 4 E4B (Effective 4B)
4B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 8.3 GBHeadroom: 15.7 GBTTFT: fast
ollama run gemma4:e4b
154
tok/s
Estimated
Weights
4.25 GB
KV cache
2.00 GB
Activations
0.22 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~124 ms (fast)
Model details →
#3Command R7B (12-2024)
8B
command-r
Quant: Q4_K_MContext: 8,192VRAM: 10.9 GBHeadroom: 13.1 GBTTFT: fast
136
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): ~248 ms (fast)
Model details →
#4Ministral 3B Instruct
3B
mistral
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 →
#5Ministral 8B Instruct
8B
mistral
Quant: Q4_K_MContext: 8,192VRAM: 10.9 GBHeadroom: 13.1 GBTTFT: fast
136
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): ~248 ms (fast)
Model details →
#6Codestral Mamba 7B
7B
mistral
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 →
#7Falcon Mamba 7B
7B
falcon
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 →
#8Qwen 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 →
#9Qwen 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 →
#10Qwen 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 →
#11Qwen 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 →
#12InternLM 2.5 7B Chat
7B
internlm
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 →

Runs with tradeoffs
52 models

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

Nemotron 3 Nano (30B-A3B)
30B
other
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 nemotron3:nano
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 →
Jamba 1.5 Mini
52B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 41.3 GBHeadroom: 1.9 GBTTFT: fast
  • • Partial CPU offload: ~42% of layers run on CPU
90
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): ~372 ms (fast)
Model details →
Mistral Nemo 12B Instruct
12B
mistral
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 21.2 GBHeadroom: 2.8 GBTTFT: fast
  • • Tight VRAM fit — only 2.8 GB headroom left for context growth
ollama run mistral-nemo:12b
51
tok/s
Estimated
Weights
12.75 GB
KV cache
6.00 GB
Activations
0.65 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~372 ms (fast)
Model details →
Gemma 4 Turkish 26B (4B active)
26B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 21.5 GBHeadroom: 2.5 GBTTFT: noticeable
  • • Tight VRAM fit — only 2.5 GB headroom left for context growth
42
tok/s
Estimated
Weights
15.70 GB
KV cache
3.25 GB
Activations
0.79 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~806 ms (noticeable)
Model details →
Gemma 3 27B
27B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 22.3 GBHeadroom: 1.7 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.7 GB headroom left for context growth
ollama run gemma3:27b
40
tok/s
Estimated
Weights
16.30 GB
KV cache
3.38 GB
Activations
0.82 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~837 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 →

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.