01
Qwen3.5 9B Instruct (Q8)
Qwen / 9B / Q8_0 / ~10.7 GB
Best for: Quality, Coding, Reasoning·Pop: 86/100
Perf: ~44 tok/s · first token ~0.4s
Local OKOK
Fits in 16 GB VRAM with room to spare. Best for quality, coding, reasoning on RTX 4080 SUPER.
Best Local AI Models for RTX 4080 SUPER (16GB)
The RTX 4080 SUPER delivers near-flagship performance with 16GB GDDR6X. It runs 8B models at an estimated 79 tokens per second and 14B models at around 49 tok/s. Its high memory bandwidth makes it one of the fastest 16GB cards available.
Quick answer
The best local LLM for the RTX 4080 SUPER is Qwen3.5 9B Instruct (Q8) at ~44 tok/s on its 16GB VRAM. It uses ~10.7GB of VRAM; the RTX 4080 SUPER handles up to 14b parameter models at Q4. A 14B model runs at ~49 tok/s.
$ollama run qwen3.5:9b-q8_0
TOP PICK
Qwen3.5 9B Instruct (Q8)
EST. SPEED
~44 tok/s
VRAM NEEDED
~10.7 GB
Speeds are ModelFit estimates from memory bandwidth and model size, not measured benchmarks.
RTX 4080 SUPER Estimated Tokens/sec by Model Size
Q4_K_M · ModelFit estimate| Model Size | Est. Speed | Fit on 16GB |
|---|---|---|
| 7B | ~88 tok/s | Fits in VRAM |
| 14B | ~49 tok/s | Fits in VRAM |
| 20B MoE (3.6B active) | ~75 tok/s | Fits in VRAM |
| 32B | ~5 tok/s | CPU offload (slow) |
| 35B MoE (3B active) | ~48 tok/s | CPU offload (slow) |
| 70B | ~1 tok/s | CPU offload (slow) |
| 120B MoE (5.1B active) | ~11 tok/s | CPU offload (slow) |
ModelFit estimates, not measured benchmarks: anchored to an 8B-class Q4_K_M model at 16K context on the RTX 4080 SUPER's 736 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 16GB VRAM; dense models slow to a crawl there, MoE models degrade less because hot experts stay GPU-resident.
Context costs VRAM too. Qwen3.5 9B Instruct (Q8) loads ~10.7 GB of weights; at 16k context the KV cache adds ~0.5 GB (still fits the ~14 GB usable VRAM), and at 64k it adds ~2.0 GB (still fits).
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 4080 SUPER
≈ $1,597 streetStorage & accessories for your model library
Internal NVMe SSD · 2TB~$170
A Gen4 M.2 drive keeps your whole GGUF and quant collection on fast local storage, loading models straight off NVMe.
Check price on AmazonUSB4 NVMe Enclosure~$80
40Gbps external storage fast enough to run models from. Pair it with an M.2 drive for a portable model vault.
Check price on AmazonModelFit may earn a commission on purchases through these links, at no extra cost to you. Prices shown are approximate street references.
RTX 4080 SUPER VRAM for AI: What Actually Fits?
16GB GDDR6X at 736 GB/s puts the 4080 SUPER near the top of 16GB cards in bandwidth. It handles 14B models at Q4 with ease (an estimated 49 tok/s), and 8B models fly at ~79 tok/s. The 736 GB/s bandwidth sits between the 5070 Ti (896) and 4070 Ti SUPER (672). At its MSRP of $1,597, the value proposition is weak compared to the $749 RTX 5070 Ti. Best considered by existing owners or on the used market.
RTX 4080 SUPER vs Similar GPUs
| Hardware | Memory | Speed | Bandwidth | Price |
|---|---|---|---|---|
| RTX 5080 | 16 GB | 94 tok/s | 960 GB/s | $999 |
| RTX 4070 Ti SUPER | 16 GB | 72 tok/s | 672 GB/s | $1,148 |
| RTX 4080 SUPER | 16 GB | 79 tok/s | 736 GB/s | $1,597 |
| RTX 4090 | 24 GB | 104 tok/s | 1008 GB/s | $2,574 |
Recommended Models
registry-verified10 models02
Gemma 4 12B
Gemma / 12B / Q4_K_M / ~8 GB
Best for: Chat, Coding, Multimodal·Pop: 80/100
Perf: ~56 tok/s · first token ~0.4s
Local OKExcellent
Fits in 16 GB VRAM with room to spare. Best for chat, coding, multimodal on RTX 4080 SUPER.
03
Qwen3 14B
Qwen / 14B / Q4_K_M / ~11 GB
Best for: Coding, Quality·Pop: 84/100
Perf: ~49 tok/s · first token ~0.4s
Local OKOK
Fits in 16 GB VRAM with room to spare. Best for coding, quality on RTX 4080 SUPER.
04
Gemma 3 12B Instruct
Gemma / 12B / Q4_K_M / ~9.5 GB
Best for: Chat, Quality·Pop: 76/100
Perf: ~56 tok/s · first token ~0.4s
Local OKExcellent
Fits in 16 GB VRAM with room to spare. Best for chat, quality on RTX 4080 SUPER.
05
Mistral Nemo 12B
Mistral / 12B / Q4_K_M / ~9.5 GB
Best for: Chat, Translation·Pop: 78/100
Perf: ~56 tok/s · first token ~0.4s
Local OKExcellent
Fits in 16 GB VRAM with room to spare. Best for chat, translation on RTX 4080 SUPER.
06
Llama 3.1 8B Instruct (Q5)
Llama / 8B / Q5_K_M / ~8 GB
Best for: Chat, Coding·Pop: 68/100
Perf: ~68 tok/s · first token ~0.4s
Local OKExcellent
Fits in 16 GB VRAM with room to spare. Best for chat, coding on RTX 4080 SUPER.
07
GPT-OSS 20B
GPT-OSS / 21B / MXFP4 / ~13.8 GB
Best for: Chat, Coding, Reasoning·Pop: 85/100
Perf: ~66 tok/s · first token ~0.4s
Local OKOK
Fits in 16 GB VRAM with room to spare. Best for chat, coding, reasoning on RTX 4080 SUPER.
08
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: ~89 tok/s · first token ~0.4s
Local OKOK
Fits in 16 GB VRAM with room to spare. Best for local ai agents, privacy-first tool calling, mcp workflows on RTX 4080 SUPER.
09
Qwen3.5 9B Instruct
Qwen / 9B / Q4_K_M / ~7 GB
Best for: Quality, Coding, Reasoning·Pop: 86/100
Perf: ~72 tok/s · first token ~0.4s
Local OKExcellent
Fits in 16 GB VRAM with room to spare. Best for quality, coding, reasoning on RTX 4080 SUPER.
10
Qwen2.5 Coder 14B
Qwen / 14B / Q4_K_M / ~11 GB
Best for: Coding·Pop: 68/100
Perf: ~49 tok/s · first token ~0.4s
Local OKOK
Fits in 16 GB VRAM with room to spare. Best for coding on RTX 4080 SUPER.
Models Too Big for 16GB? Rent a Cloud GPU
by the hourThe RTX 4080 SUPER tops out around up to 14b 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.
Similar GPUs for Local AI
Compatible Model Families
Qwen
Alibaba Cloud: Widest size range (0.5B to 235B)
LlamaMeta: Most popular open-weight model family
DeepSeekDeepSeek AI: Best-in-class reasoning with R1 models
MistralMistral AI: Excellent performance-per-parameter ratio
GemmaGoogle DeepMind: Excellent quality at small sizes (1B-9B)
PhiMicrosoft: Best quality-per-gigabyte at small sizes
RTX 4080 SUPER FAQ: Common Questions
How much VRAM does the RTX 4080 SUPER have for LLMs?
The RTX 4080 SUPER has 16GB GDDR6X VRAM with 736 GB/s bandwidth. About 15.5GB is usable. Same capacity as the 4070 Ti SUPER and 5070 Ti, but higher bandwidth for faster inference.
What size LLM can I run on an RTX 4080 SUPER?
Up to 14B parameter models at Q4 quantization. This includes all popular 14B models like DeepSeek-R1 14B and Qwen 2.5 14B. At an estimated 49 tok/s on 14B (79 on 8B), responses feel fast for chat workloads.
Is the RTX 4080 SUPER good for local AI?
It is excellent for AI performance but poor value at MSRP. The RTX 5070 Ti costs less than half the price and delivers similar speed (an estimated 87 vs 79 tok/s on 8B). Buy the 4080 SUPER only on the used market at $800-900.
Should I upgrade from RTX 4080 SUPER to RTX 5080?
The RTX 5080 is 19% faster (an estimated 94 vs 79 tok/s on 8B) at a lower MSRP ($999 vs $1,597). Both have 16GB VRAM. If you already own the 4080 SUPER, the upgrade is modest. If buying new, skip to the 5080.
How fast is a 27B-class model on the RTX 4080 SUPER?
The RTX 4080 SUPER's 16GB of VRAM cannot fit a 32B model comfortably. The largest size class it fits is 20B MoE (3.6B active), at an estimated 75 tok/s.
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.