What models can the NVIDIA GeForce RTX 4070 run?

With 12GB of VRAM: qwen3:0.6b, qwen3:1.7b, qwen3:4b, qwen3:8b, qwen3:14b, qwen2.5vl:7b, llama3.1:8b, llama3.2:1b run fully in VRAM. AD104, 5888 CUDA. Best LocalScore 8B median in this 7-card set (76.3 tok/s) — strong price/perf for 7-8B serving.

Is the NVIDIA GeForce RTX 4070 still worth using for local LLMs in 2026?

computed band 45.0-75.0 tok/s for 8B Q4_K_M (roofline, 504 GB/s VRAM); community: 76.3 tok/s generation median (LocalScore 838) tok/s Llama 3.1 8B Instruct Q4_K_M (https://www.localscore.ai/accelerator/147) AD104, 5888 CUDA. Best LocalScore 8B median in this 7-card set (76.3 tok/s) — strong price/perf for 7-8B serving. For serious work, the upgrade path is: rtx-4070-ti-super, rtx-4090.

▲ local intelligence

will it local

Best local LLMs for the NVIDIA GeForce RTX 4070

12GB · Ada

AD104, 5888 CUDA. Best LocalScore 8B median in this 7-card set (76.3 tok/s) — strong price/perf for 7-8B serving.

→explore the full catalogupgrade paths with live prices · what fits on each machine

Speed

computed band 45.0-75.0 tok/s for 8B Q4_K_M (roofline, 504 GB/s VRAM); community: 76.3 tok/s generation median (LocalScore 838) tok/s Llama 3.1 8B Instruct Q4_K_M (https://www.localscore.ai/accelerator/147)

Effective decode window: 0.46–0.76 of 504 GB/s nominal → ~232–383 GB/s effective (llama.cpp decode, Q4_K_M basis; arch window, community-calibrated)

Community check — localmaxxing.com medians (1 bucket): localmaxxing.com

→ ~40 tok/s · 12-15B Q4 · 5 runs · inside our computed band

What fits (computed)

→ 13b-q4 offload-partial 14.6 GB vs 12 GB usable — partial CPU offload, expect large speed loss

→ 3b-q4 full 2.8 GB needed of 12 GB usable — headroom for context

→ 4b-q4 full 3.7 GB needed of 12 GB usable — headroom for context

→ 8b-q4 full 6.1 GB needed of 12 GB usable — headroom for context

Cited community benches (1 rows)

→ 76.3 tok/s generation median (LocalScore 838) tok/s · Llama 3.1 8B Instruct Q4_K_M LocalScore median · source

Runs fully in memory (machine alternatives)

Nominal bandwidth: 504 GB/s — see the effective decode window above

→ qwen3:0.6b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 0.6B · 0.6GB · needs ~1GB (4k ctx)

→ qwen3:1.7b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 1.7B · 1.4GB · needs ~1.8GB (4k ctx)

→ qwen3:4b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 4B · 2.6GB · needs ~3.2GB (4k ctx)

→ llama3.2:1b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 1B · 1.3GB · needs ~1.4GB (4k ctx)

→ llama3.2:3b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 3B · 2.0GB · needs ~2.4GB (4k ctx)

→ gemma3:1b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 1B · 1.0GB · needs ~1.1GB (4k ctx)

→ phi4:mini on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) mini 3.8B · 2.5GB · needs ~3GB (4k ctx)

→ moondream:2b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 2B · 1.7GB · needs ~3.7GB (4k ctx)

→ whisper:tiny on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) tiny · 0.1GB · needs ~2.1GB (4k ctx)

→ whisper on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) base · 0.3GB · needs ~2.3GB (4k ctx)

→ whisper:small on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) small · 0.9GB · needs ~2.9GB (4k ctx)

→ whisper:medium on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) medium · 3.1GB · needs ~5.1GB (4k ctx)

→ kokoro:82m on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 82M · 0.3GB · needs ~2.3GB (4k ctx)

→ gemma3:4b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 4B · 3.3GB · needs ~3.8GB (4k ctx)

→ deepseek-r1:7b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) distill 7B · 4.7GB · needs ~4.9GB (4k ctx)

→ mistral:7b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 7B · 4.1GB · needs ~4.6GB (4k ctx)

→ llava:7b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 7B · 4.7GB · needs ~6.7GB (4k ctx)

→ qwen3:8b on Tesla P100 (16GB, used) ($135) 8B · 5.2GB · needs ~5.8GB (4k ctx)

→ qwen2.5vl:7b on Tesla P100 (16GB, used) ($135) 7B · 5.6GB · needs ~5.8GB (4k ctx)

→ llama3.1:8b on Tesla P100 (16GB, used) ($135) 8B · 4.9GB · needs ~5.4GB (4k ctx)

→ deepseek-r1:8b on Tesla P100 (16GB, used) ($135) distill 8B · 4.9GB · needs ~5.4GB (4k ctx)

→ whisper:large-v3 on Tesla P100 (16GB, used) ($135) large-v3 · 6.2GB · needs ~8.2GB (4k ctx)

→ mistral-nemo:12b on Tesla P100 (16GB, used) ($135) 12B · 7.1GB · needs ~7.7GB (4k ctx)

→ sdxl on Tesla P100 (16GB, used) ($135) SDXL base · 6.9GB · needs ~8.9GB (4k ctx)

→ llava:13b on Tesla P100 (16GB, used) ($135) 13B · 8.0GB · needs ~11.1GB (4k ctx)

→ gemma3:12b on Tesla P100 (16GB, used) ($135) 12B · 8.1GB · needs ~9.6GB (4k ctx)

→ qwen3:14b on Tesla P100 (16GB, used) ($135) 14B · 9.3GB · needs ~9.9GB (4k ctx)

→ deepseek-r1:14b on Tesla P100 (16GB, used) ($135) distill 14B · 9.0GB · needs ~9.8GB (4k ctx)

→ phi4:14b on Tesla P100 (16GB, used) ($135) 14B · 9.1GB · needs ~9.9GB (4k ctx)

Borderline — runs, but offloads

→ gpt-oss:20b 20B MoE — 14.2 GB vs 12 GB usable — partial CPU offload, expect large speed loss

Gotchas

⚠ 12GB + 192-bit bus: 8B Q4 is comfortable, 14B Q4_K_M fits but leaves little headroom for long context/KV cache

⚠ Weakest full AD104 (5888 CUDA, 46 RT cores); supers made it look worse — still 504 GB/s, same as 4070 Super/Ti

⚠ Avoid confusion with RTX 4070 Laptop GPU (8GB, much slower)

⚠ Memory clock 1313 MHz (21 Gbps effective)

Where to go next

rtx-4070-ti-super

+4GB VRAM, 672 GB/s (+33%)

→ its best-models page

rtx-4090

24GB / 1008 GB/s for 30B-class

→ its best-models page

2026-09-18 · ← full hardware catalog · fit = working set vs VRAM · speeds are community-reported, cited in our knowledge base