Best Local AI Models for RTX 4090 (24GB)

The RTX 4090 pairs 24GB of GDDR6X with 1,008 GB/s of memory bandwidth. It runs 8B chat models at an estimated 104 tok/s and 32B reasoning models at an estimated 32 tok/s. Only the RTX 5090 is faster among consumer cards.

24GB VRAM
Quick answer

The best local LLM for the RTX 4090 is Gemma 4 26B-A4B at ~85 tok/s on its 24GB VRAM. It uses ~16GB of VRAM; the RTX 4090 handles up to 32B parameter models at Q4. A 32B model at Q4 runs at ~32 tok/s.

Sizing rule: a Q4 model needs about 0.6 GB of VRAM per billion parameters, and ModelFit budgets 90% of this card's 24GB for weights, context, and KV-cache. The per-size table below uses that same budget. Other strong fits: Qwen3.8 27B (27B, ~16.5GB) and Qwen3.5 27B Instruct (27B, ~16GB). Gemma 4 26B-A4B runs at an estimated 85 tok/s on this card. What it will not run: a 70B model does not fit in VRAM alone, so it spills to system RAM over PCIe and slows sharply.

$ollama run gemma4:26b
TOP PICK
Gemma 4 26B-A4B
EST. SPEED
~85 tok/s
VRAM NEEDED
~16 GB

Speeds are ModelFit estimates from memory bandwidth and model size, not measured benchmarks.

Cite this page: ModelFit, RTX 4090 24GB Local LLM (2026): Runs 32B, Top Pick ~85 tok/s, https://modelfit.io/gpu/rtx-4090/, updated September 2026, CC BY 4.0.

Last updated: September 3, 2026 · Editor: ModelFit Team

VRAM24 GB GDDR6X
Speed (8B Q4)104 tok/s
Bandwidth1008 GB/s
ArchitectureAda Lovelace
Price · as of Jul 2026~$3,494*check live price
Max model sizeUp to 32B parameter models
Compatibility10 excellent, 0 workable

*Launch MSRP was $1,599; the card is now discontinued and current market pricing runs well above that

RTX 4090 Estimated Tokens/sec by Model Size

Q4_K_M · ModelFit estimate
Model SizeEst. SpeedFit on 24GB
7B~117 tok/sFits in VRAM
14B~65 tok/sFits in VRAM
20B MoE (3.6B active)~99 tok/sFits in VRAM
32B~32 tok/sFits in VRAM
35B MoE (3B active)~84 tok/sFits in VRAM
70B~2 tok/sCPU offload (slow)
120B MoE (5.1B active)~14 tok/sCPU offload (slow)
Bar chart: estimated tokens per second on the NVIDIA GeForce RTX 4090 by model size. 7B ~117 tok/s, 14B ~65 tok/s, 20B MoE (3.6B active) ~99 tok/s, 32B ~32 tok/s, 35B MoE (3B active) ~84 tok/s, 70B ~2 tok/s (CPU offload), 120B MoE (5.1B active) ~14 tok/s (CPU offload). ModelFit bandwidth-based estimates.
Estimated Speed by Model Size
Fits in memoryCPU offload
7B117 tok/s14B65 tok/s20B MoE (3.6B active)99 tok/s32B32 tok/s35B MoE (3B active)84 tok/s70B2 tok/s120B MoE (5.1B active)14 tok/s
ModelFit bandwidth-based estimates, not measured benchmarks.

ModelFit estimates, not measured benchmarks: anchored to an 8B-class Q4_K_M model at 16K context on the RTX 4090's 1008 GB/s bandwidth, then scaled by model size. MoE rows scale by active parameters (decode reads only the active experts), so a 35B MoE runs far faster than a dense 32B. "CPU offload" sizes exceed the 24GB VRAM; dense models slow to a crawl there, MoE models degrade less because hot experts stay GPU-resident.

Context costs VRAM too. Gemma 4 26B-A4B loads ~16 GB of weights; at 16k context the KV cache adds ~4.0 GB (still fits the ~22 GB usable VRAM), and at 64k it adds ~16.0 GB (exceeds the budget, use a smaller quant or a q8_0 KV cache).

KV-cache figures assume an fp16 cache, the llama.cpp/Ollama default. Standard GQA models use a size-class estimate (8 KV heads x 128 head dim class); hybrid linear-attention models (Qwen3.5/3.6, Qwen3-Next) use the exact per-token cost from their published config, since only their sparse full-attention layers cache KV. A q8_0 KV cache roughly halves either figure. Estimates, not measurements.

Where to Buy the RTX 4090

≈ $3,494 street · Launch MSRP was $1,599; the card is now discontinued and current market pricing runs well above that
Storage & accessories for your model library

ModelFit may earn a commission on purchases through these links, at no extra cost to you. Prices shown are approximate street references.

RTX 4090 VRAM for AI: What Actually Fits?

24GB GDDR6X at 1,008 GB/s gives the RTX 4090 real headroom. 32B models at Q4 (~20GB) load fully with 3GB left for KV cache. 14B models at Q5 or Q6 fit easily for higher quality inference. At 104 tok/s with 8B models, the 4090 delivers near-instant responses. The only consumer card faster is the RTX 5090 (145 tok/s, 32GB). Among 24GB cards, its 1,008 GB/s bandwidth is the highest ModelFit tracks.

RTX 4090 vs Similar GPUs

HardwareMemorySpeedBandwidthPrice
RTX 309024 GB87 tok/s936 GB/s$900
RTX 508016 GB94 tok/s960 GB/s$1,570
RTX 409024 GB104 tok/s1008 GB/s$3,494
RTX 509032 GB145 tok/s1792 GB/s$4,700

Recommended Models

registry-verified10 models
01

Gemma 4 26B-A4B

Gemma / 26B / Q4_K_M / ~16 GB

Best for: Chat, Coding, Multimodal·Pop: 86/100

Perf: ~85 tok/s · first token ~0.4s

Local OKOK

Fits in 24 GB VRAM with room to spare. Best for chat, coding, multimodal on RTX 4090.

ollamaregistry-verified
02

Qwen3.8 27B

Qwen / 27B / Q4_K_M / ~16.5 GB

Best for: Coding, Agent, Vision, Long context·Pop: 95/100

Perf: ~37 tok/s · first token ~0.4s

Local OKOK

Fits in 24 GB VRAM with room to spare. Best for coding, agent, vision, long context on RTX 4090.

ollamaregistry-verified
03

Qwen3.5 27B Instruct

Qwen / 27B / Q4_K_M / ~16 GB

Best for: Chat, Coding, Complex reasoning·Pop: 82/100

Perf: ~37 tok/s · first token ~0.4s

Local OKOK

Fits in 24 GB VRAM with room to spare. Best for chat, coding, complex reasoning on RTX 4090.

ollamaregistry-verified
04

GPT-OSS 20B

GPT-OSS / 21B / MXFP4 / ~13.8 GB

Best for: Chat, Coding, Reasoning·Pop: 85/100

Perf: ~87 tok/s · first token ~0.4s

Local OKExcellent

Fits in 24 GB VRAM with room to spare. Best for chat, coding, reasoning on RTX 4090.

ollamaregistry-verified
05

Qwen3.6 27B

Qwen / 27B / Q4_K_M / ~18 GB

Best for: Coding, Quality, Long context·Pop: 92/100

Perf: ~37 tok/s · first token ~0.4s

Local OKOK

Fits in 24 GB VRAM with room to spare. Best for coding, quality, long context on RTX 4090.

ollamaregistry-verified
06

LFM2 24B-A2B Instruct

LFM2 / 24B / Q4_K_M / ~14 GB

Best for: Local AI agents, privacy-first tool calling, MCP workflows·Pop: 80/100

Perf: ~118 tok/s · first token ~0.3s

Local OKExcellent

Fits in 24 GB VRAM with room to spare. Best for local ai agents, privacy-first tool calling, mcp workflows on RTX 4090.

ollamaregistry-verified
07

Gemma 4 12B (Q8)

Gemma / 12B / Q8_0 / ~12.8 GB

Best for: Chat, Coding, Multimodal·Pop: 80/100

Perf: ~46 tok/s · first token ~0.4s

Local OKExcellent

Fits in 24 GB VRAM with room to spare. Best for chat, coding, multimodal on RTX 4090.

ollamaregistry-verified
08

Qwen3.5 35B-A3B Instruct

Qwen / 35B / Q4_K_M / ~20 GB

Best for: Reasoning, Coding, Agent scenarios·Pop: 90/100

Perf: ~84 tok/s · first token ~1.0s

Local OKOK

Fits in 24 GB VRAM with room to spare. Best for reasoning, coding, agent scenarios on RTX 4090.

ollamaregistry-verified
09

Qwen3 14B

Qwen / 14B / Q4_K_M / ~11 GB

Best for: Coding, Quality·Pop: 84/100

Perf: ~65 tok/s · first token ~0.4s

Local OKExcellent

Fits in 24 GB VRAM with room to spare. Best for coding, quality on RTX 4090.

ollamaregistry-verified
10

Qwen3 14B (Q8)

Qwen / 14B / Q8_0 / ~15.9 GB

Best for: Coding, Quality·Pop: 84/100

Perf: ~40 tok/s · first token ~0.4s

Local OKOK

Fits in 24 GB VRAM with room to spare. Best for coding, quality on RTX 4090.

ollamaregistry-verified

Models Too Big for 24GB? Rent a Cloud GPU

by the hour

The RTX 4090 tops out around up to 32b parameter models. For anything bigger, an hourly rented GPU runs the same open weights with the same Ollama workflow, billed by the hour, no hardware purchase needed.

RunPodHourly GPU pods (RTX 4090 to H100) with one-click Ollama/vLLM templates.Rent
Vast.aiMarketplace of rented GPUs, usually the cheapest per-hour prices.Rent

ModelFit may earn a commission on sign-ups made through these links, at no extra cost to you.

RTX 4090 FAQ: Common Questions

How much VRAM does the RTX 4090 have for LLMs?

The RTX 4090 has 24GB GDDR6X VRAM with 1,008 GB/s bandwidth. About 23GB is usable for models. It runs 32B models at Q4 with room for 8K+ context windows.

What size LLM can I run on an RTX 4090?

Up to 32B parameter models at Q4 quantization. This includes DeepSeek-R1 32B, Qwen 2.5 32B, and larger reasoning models. For 70B models, you need Q2 or dual GPUs, or step up to the RTX 5090.

Is the RTX 4090 worth its 2026 price for AI?

Rarely. The card is discontinued and its street price has climbed well past launch MSRP, while a used RTX 3090 offers 83% of the speed with the same 24GB VRAM for a fraction of the money. The 4090 is worth it if you also game at 4K or need the absolute fastest 24GB card. For pure AI value, the 3090 wins.

RTX 4090 vs RTX 5090 for AI: which is better?

The RTX 5090 is 39% faster on 8B models (an estimated 145 vs 104 tok/s) with 8GB more VRAM (32 vs 24GB), enabling 70B models. The 5090 also costs more in 2026 now that the 4090 is discontinued and only scalped stock remains. If buying new, the 5090 is the clear choice.

Can the RTX 4090 run 70B models?

Not at full quality. A 70B Q4 model needs ~42GB VRAM. The 4090 has 24GB, so you would need Q2 quantization (lower quality) or run with partial CPU offloading (much slower). For 70B, the RTX 5090 (32GB) is recommended.

How fast is a 27B-class model like Qwen3.8 27B on the RTX 4090?

ModelFit estimates a 32B model on the RTX 4090 runs at roughly 32 tok/s at Q4_K_M. The current 27B-class pick in the catalog is Qwen3.8 27B (ollama run qwen3.8:27b).

The weekly local-AI refresh

New open-weight models, real Apple Silicon benchmarks, and the one model worth running on your Mac this week. Free, one email a week, unsubscribe anytime.

By subscribing you agree to our Privacy Policy and to receive the weekly email. Unsubscribe anytime.

Want Personalized Recommendations?

Use our interactive wizard to compare models across Apple Silicon and NVIDIA GPUs.