Qwen3.5 9B Instruct
Local OKExcellentA · 35
Best for: Quality, Coding, Reasoning·Pop: 86/100
Perf: est. 78 tok/s, typical error 5% · first token ~0.3s
Fits in 12 GB VRAM with room to spare. Best for quality, coding, reasoning on RTX 4070.
Best Local AI Models for RTX 4070 (12GB)
The RTX 4070 delivers strong mid-range performance with 12GB GDDR6X memory. On 8B models it reaches est. 73 tok/s, typical error 5%, excellent speed for 7B-8B parameter models at a reasonable price point.
Quick answer
The best local LLM for the RTX 4070 is Qwen3.5 9B Instruct (est. 78 tok/s, typical error 5%) on its 12GB VRAM. It uses ~7GB of VRAM; the RTX 4070 handles up to 9B parameter models at Q4. A 14B model at Q4 runs at est. 44 tok/s, typical error 15%. (ModelFit, 2026)
Sizing rule: a Q4 model needs about 0.6 GB of VRAM per billion parameters, and ModelFit budgets 90% of this card's 12GB for weights, context, and KV-cache. The per-size table below uses that same budget. Other strong fits: Gemma 4 12B (12B, ~8GB) and Ornith 1.0 9B (9B, ~5.6GB). On this card Qwen3.5 9B Instruct runs at est. 78 tok/s, typical error 5%. What it will not run: a 20B MoE (3.6B active) model does not fit in VRAM alone, so it spills to system RAM over PCIe and slows sharply.
$ollama run qwen3.5:9b
- Top pick
- Qwen3.5 9B Instruct
- Decode speed
- est. 78 tok/s, typical error 5%
- VRAM needed
- ~7 GB
Speeds are ModelFit estimates from memory bandwidth and model size, not measured benchmarks. Typical error: the median gap between the ModelFit speed model and measured runs on hardware the model was not fitted on, for this backend and model size.
Cite this page: ModelFit, RTX 4070 12GB Local LLM (2026): Fast 7B-9B, est. 73 tok/s, https://modelfit.io/gpu/rtx-4070/, updated October 2026, CC BY 4.0.
Specs
VRAM
12 GB GDDR6X
Speed (8B Q4)
est. 73 tok/stypical error 5%
Bandwidth
504 GB/s
Architecture
Ada Lovelace
Max model size
Up to 9B parameter models
Compatibility
10 excellent, 0 workable
Vendor
Table 1
RTX 4070 estimated tokens/sec by model size
Q4_K_M · ModelFit estimate| Model size | Est. speed | Fit on 12GB |
|---|---|---|
| 7B | est. 84 tok/stypical error 5% | Fits in VRAM |
| 14B | est. 44 tok/stypical error 15% | Fits in VRAM |
| 20B MoE (3.6B active) | est. 73 tok/stypical error 15% | CPU offload (slow) |
| 32B | est. 2 tok/stypical error 5% | CPU offload (slow) |
| 35B MoE (3B active) | est. 40 tok/stypical error 15% | CPU offload (slow) |
| 70B | est. 1 tok/stypical error 10% | CPU offload (slow) |
| 120B MoE (5.1B active) | est. 25 tok/stypical error 15% | CPU offload (slow) |
Fig. 1RTX 4070: estimated speed by model size
Decode speed, generic Q4_K_M model of each size at 4K context, 504 GB/s, typical error 5-15%
Fits in 12 GBCPU offload (slow)
7B84
14B44
20B MoE (3.6B active)73
32B2
35B MoE (3B active)40
70B1
120B MoE (5.1B active)25
tok/s est.ModelFit estimates, not measured benchmarks: decode speed of a generic Q4_K_M model of each size at 4K context on the RTX 4070's 504 GB/s bandwidth. 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 12GB VRAM; dense models slow to a crawl there, MoE models degrade less because hot experts stay GPU-resident. What typical error means.
Fig. 2
Context costs VRAM too.
Qwen3.5 9B Instruct loads ~7 GB of weights; at 16k context the KV cache adds ~0.5 GB (still fits the ~11 GB usable VRAM), and at 64k it adds ~2.0 GB (still fits).
Weights 7.0 GBKV cache · 16k context 0.5 GBHeadroom 3.3 GBRuntime reserve 1.2 GB
The model leaves about 3.3 GB of the usable VRAM budget free after weights and 16k context.
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.
Get told when a model beats Qwen3.5 9B Instruct on your RTX 4070
One email when a new open-weight model is a better fit for 12 GB of VRAM, plus the Thursday weekly.
You'll also get the weekly ModelFit email. By signing up you agree to our Privacy Policy. Unsubscribe from either email anytime, in one click.
Where to buy the RTX 4070
Storage & accessories for your model library
- Internal NVMe SSD · 2TBA Gen4 M.2 drive keeps your whole GGUF and quant collection on fast local storage, loading models straight off NVMe.Check price on Amazon
- USB4 NVMe Enclosure40Gbps external storage fast enough to run models from. Pair it with an M.2 drive for a portable model vault.Check price on Amazon
ModelFit may earn a commission on purchases through these links, at no extra cost to you.
RTX 4070 VRAM for AI: what actually fits?
12GB GDDR6X at 504 GB/s puts the RTX 4070 among the fastest 12GB cards from the previous generation, level with the 4070 SUPER. The higher bandwidth compared to the RTX 3060 (504 vs 360 GB/s) translates directly to faster token generation. You get the same model capacity as the 3060 but 46% more speed. For 7B-9B models at Q4, expect 4-6GB usage with solid headroom for context.
Table 2
RTX 4070 vs similar GPUs
| Hardware | Memory | Speed | Bandwidth |
|---|---|---|---|
| RTX 3060 | 12 GB | est. 50 tok/stypical error 5% | 360 GB/s |
| RTX 4070 | 12 GB | est. 73 tok/stypical error 5% | 504 GB/s |
| RTX 4070 SUPER | 12 GB | est. 73 tok/stypical error 5% | 504 GB/s |
| RTX 5070 | 12 GB | est. 98 tok/stypical error 5% | 672 GB/s |
Recommended models
registry-verified10 modelsGemma 4 12B
Local OKOKB · 26
Best for: Chat, Coding, Multimodal·Pop: 80/100
Perf: est. 52 tok/s, typical error 15% · first token ~0.4s
Fits in 12 GB VRAM with room to spare. Best for chat, coding, multimodal on RTX 4070.
Ornith 1.0 9B
Local OKExcellentA · 48
Best for: Agentic coding on small machines·Pop: 76/100
Perf: est. 78 tok/s, typical error 5% · first token ~0.3s
Fits in 12 GB VRAM with room to spare. Best for agentic coding on small machines on RTX 4070.
Mellum2.1 12B-A2.5B Thinking
Local OKOKB · 25
Best for: Agentic coding, Small machines·Pop: 76/100
Perf: est. 141 tok/s, typical error 15% · first token ~0.1s
Fits in 12 GB VRAM with room to spare. Best for agentic coding, small machines on RTX 4070.
Gemma 4 E4B (Q8)
Local OKExcellentA · 31
Best for: On-device, Mobile, Chat·Pop: 82/100
Perf: est. 79 tok/s, typical error 5% · first token ~1.5s
Fits in 12 GB VRAM with room to spare. Best for on-device, mobile, chat on RTX 4070.
LFM2.5 8B-A1B
Local OKExcellentA · 49
Best for: On-device agents, tool calling, multilingual chat·Pop: 72/100
Perf: est. 196 tok/s, typical error 15% · first token ~0.1s
Fits in 12 GB VRAM with room to spare. Best for on-device agents, tool calling, multilingual chat on RTX 4070.
NVIDIA Nemotron 3.5 Bolt E4B
Local OKOKB · 27
Best for: Voice assistants, Tool calling, Chat·Pop: 75/100
Perf: est. 98 tok/s, typical error 5% · first token ~0.3s
Fits in 12 GB VRAM with room to spare. Best for voice assistants, tool calling, chat on RTX 4070.
MiMo-V2.6-Distill-Qwen-9B
Local OKExcellentA · 46
Best for: Agentic coding, Small machines·Pop: 60/100
Perf: est. 76 tok/s, typical error 5% · first token ~0.3s
Fits in 12 GB VRAM with room to spare. Best for agentic coding, small machines on RTX 4070.
Granite Switch 4.1 8B
Local OKExcellentA · 41
Best for: Chat, Decisions, Safety checks·Pop: 64/100
Perf: est. 57 tok/s, typical error 5% · first token ~0.3s
Fits in 12 GB VRAM with room to spare. Best for chat, decisions, safety checks on RTX 4070.
Ministral 3 8B
Local OKExcellentA · 44
Best for: Chat, Coding, Vision·Pop: 74/100
Perf: est. 65 tok/s, typical error 5% · first token ~0.3s
Fits in 12 GB VRAM with room to spare. Best for chat, coding, vision on RTX 4070.
Video and image models on the RTX 4070
Runs · Stated: the linked source says a GPU with that much VRAM runs the model. Runs · Published: a dated run on the named card with that much VRAM. unknown: no source yet. Exceeds VRAM: the complete download is larger than 12 GB, so part of it has to sit in system RAM. Every VRAM tier: video · image.
Video
| Model | Fits | Quality | App |
|---|---|---|---|
| HunyuanVideo-1.5Tencent Hunyuan Community License | Runs · PublishedRTX 4070 · 12 GB VRAM · ComfyUI example workflow, 480p I2V distilled fp8, 81 frames · ComfyUI issue #10855 | #38 of 48 in text to video4,292 votessnapshot 2026-09-22 | ComfyUI |
| LTX-2.3LTX-2 Community License Agreement | Runs · PublishedRTX 4060 · 8 GB VRAM · ComfyUI GGUF workflow, 720p 5 s in about 190 s, 32 GB RAM · ComfyUI issue #14345 | No independent score yet | Lightricks/LTX-2 ltx-pipelines, ComfyUI |
| LTX-2.5LTX-2.x Community License Agreement | Runs · Stated12 GB VRAM · LTX Desktop on Windows, weight streaming, 40 GB RAM, 540p · LTX Desktop compatibility matrix (Lightricks) | No independent score yet | Lightricks/LTX-2 ltx-pipelines, ComfyUI |
| MiniMax H3MiniMax H3 Community License Agreement | Runs · Stated12 GB VRAM · Diffusers int8, streamed blocks, 960x544, about 75 GB system RAM · Diffusers docs: MiniMax-H3 memory | #8 of 48 in text to video11,417 votessnapshot 2026-09-22 | stable-diffusion.cpp, ComfyUI |
| Wan2.2 A14BApache License 2.0 | Runs · PublishedRTX 2060 · 6 GB VRAM · ComfyUI Q8 GGUF, 480x720, 81 frames, 7 to 10 min, 28 GB RAM plus a 60 GB page file · ComfyUI issue #12451 | #42 of 48 in text to video10,458 votessnapshot 2026-09-22 | ComfyUI |
| Wan2.2 TI2V 5BApache License 2.0 | Runs · Stated8 GB VRAM · ComfyUI native offloading · ComfyUI docs: Wan2.2Complete: Comfy-Org repackaged FP16 with FP8 scaled UMT518.1 GB download | No independent score yet | ComfyUI |
| Mochi 1 previewApache License 2.0 | unknownComplete: calcuis GGUF Q3_K_M with Q4_0 T5 and FP8 VAE7.7 GB download | #48 of 48 in text to video5,893 votessnapshot 2026-09-22 | Diffusers, ComfyUI |
Quality: blind human votes from Arena (arena.ai), CC BY 4.0, snapshot 2026-09-22. Scores are for the Arena checkpoint, not your local quantized build.
Image
| Model | Fits | Quality | App |
|---|---|---|---|
| FLUX 3 Image KleinFLUX Kommunity License v1.0 | Runs · Stated8 GB VRAM · official ComfyUI int8 files · FLUX 3 Image Klein README (Black Forest Labs) | No independent score yet | Diffusers |
| FLUX.1 [dev]FLUX.1 [dev] Non-Commercial License v1.1.1 | Runs · Stated6 GB VRAM · stable-diffusion.cpp with GGUF weights · stable-diffusion.cpp FLUX docs | #78 of 82 in text to image49,221 votessnapshot 2026-10-07 | Diffusers, ComfyUI |
| Krea 2 TurboKrea 2 Community License Agreement v.1 | Runs · PublishedRTX 4070 · 12 GB VRAM · ComfyUI fp8, dynamic VRAM paging, 8 steps · ComfyUI issue #15365 | No independent score yet | Diffusers, stable-diffusion.cpp |
| Qwen-Image-2.1Qwen Research License Agreement | Runs · PublishedRTX 5070 Ti Laptop · 12 GB VRAM · stable-diffusion.cpp Q6_K, offload to CPU, 1024x1024 · stable-diffusion.cpp issue #2118 | #19 of 82 in text to image11,441 votessnapshot 2026-10-07 | Diffusers, stable-diffusion.cpp |
| SDXL Base 1.0CreativeML Open RAIL++-M License | Runs · Stated8 GB VRAM · SDXL 1.0, no app named · SDXL 1.0 announcement (Stability AI) | No independent score yet | ComfyUI, stable-diffusion.cpp |
| Stable Diffusion 3.5 LargeStability AI Community License | Runs · Stated11 GB VRAM · FP8 TensorRT build on RTX 40 and 50 · Stability AI: SD3.5 TensorRT models | #81 of 82 in text to image23,396 votessnapshot 2026-10-07 | ComfyUI |
| Z-Image-TurboApache 2.0 | Runs · Stated4 GB VRAM · stable-diffusion.cpp with GGUF weights · stable-diffusion.cpp Z-Image docs | #59 of 82 in text to image24,808 votessnapshot 2026-10-07 | Diffusers, stable-diffusion.cpp |
| FLUX.2 [dev]FLUX Non-Commercial License | Exceeds VRAMComplete: Q4_K_M GGUF34.8 GB download | #38 of 82 in text to image77,988 votessnapshot 2026-10-07 | Diffusers, ComfyUI, stable-diffusion.cpp |
| FLUX.2 [klein]Apache 2.0 (4B), FLUX Non-Commercial License (9B) | Exceeds VRAMComplete: Klein 4B Q8_0 GGUF12.5 GB download | No independent score yet | Diffusers, stable-diffusion.cpp |
Quality: blind human votes from Arena (arena.ai), CC BY 4.0, snapshot 2026-10-07. Scores are for the Arena checkpoint, not your local quantized build.
Can I run it on the RTX 4070?
Per-model verdict pages for this exact card: weights, KV cache by context length, and estimated tok/s, each derived from the same engine the recommendations above use.
- Qwen3 8B Q4_K_Mfits
- Qwen3 14B Q4_K_Mtight
- GPT-OSS 20B MXFP4tight
- Qwen3.8 27B Q4_K_Mno
- Llama 3.3 70B Instruct Q4_K_Mno
- Qwen3.5 35B-A3B Instruct Q4_K_Mno
- Gemma 4 26B-A4B Q4_K_Mtight
- Qwen3.5 4B Instruct Q4_K_Mfits
- Gemma 4 E4B Q4_K_Mfits
- Gemma 3 4B Instruct Q4_K_Mfits
- Llama 3.1 8B Instruct Q4_K_Mfits
- Qwen3.5 9B Instruct Q4_K_Mfits
- Gemma 4 12B Q4_K_Mfits
- Mistral Nemo 12B Q4_K_Mfits
- Qwen3.5 9B Instruct (Q8) Q8_0fits
- Gemma 4 12B (Q8) Q8_0tight
- LFM2 24B-A2B Instruct Q4_K_Mtight
- Qwen3.5 27B Instruct Q4_K_Mtight
- Qwen3.6 27B Q4_K_Mno
- Gemma 4 31B Q4_K_Mno
- Qwen3.6 35B-A3B Q4_K_Mno
- Qwen3.8 27B (Q8) Q8_0no
Similar GPUs for local AI
Speeds are estimates for Qwen3 8B Q4_K_M, typical error 5%.
Compatible model families
- QwenAlibaba Cloud: Qwen3.8 27B local flagship (Apache 2.0, vision)
- LlamaMeta: Most popular open-weight model family
- DeepSeekDeepSeek AI: V4.1 Flash: multimodal 552B MoE, API only
- MistralMistral AI: Excellent performance-per-parameter ratio
- GemmaGoogle DeepMind: Gemma 4 E4B: 4.5B effective, runs on 8GB Macs
- PhiMicrosoft: Best quality-per-gigabyte at small sizes
RTX 4070 FAQ: common questions
How much VRAM does the RTX 4070 have for LLMs?
The RTX 4070 has 12GB GDDR6X VRAM with 504 GB/s bandwidth. About 11.5GB is usable for models. Same capacity as the RTX 3060 but 40% more bandwidth, making it faster for the same models.
What size LLM can I run on an RTX 4070?
Up to 9B parameter models at Q4 quantization, same as other 12GB cards. The advantage is speed: est. 73 tok/s, typical error 5% vs est. 50 tok/s on the RTX 3060. Popular models include Qwen 2.5 7B, Llama 3.2 8B, and Gemma 2 9B.
Is the RTX 4070 good for local AI?
Yes, it is a strong mid-range choice. The 4070 offers a good balance of speed (est. 73 tok/s, typical error 5%) and price. Its main limitation is 12GB VRAM: if you need 14B models, consider the RTX 5070 Ti or 4060 Ti 16GB instead.
RTX 4070 vs RTX 5070 for AI: which should I buy?
The RTX 5070. Both launched at the same $579 MSRP, but the 2026 memory shortage inverted their street pricing: the newer 5070 now sells for noticeably LESS than the 4070, so it is 34% faster (est. 98 tok/s, typical error 5% vs est. 73 tok/s) and cheaper at once. Both have 12GB VRAM. The 4070 only makes sense well below the 5070 on the used market.
How fast is a 27B-class model on the RTX 4070?
The RTX 4070's 12GB of VRAM cannot fit a 32B model comfortably. The largest size class it fits is 14B, at est. 44 tok/s, typical error 15%. The largest individual model in the catalog that fits is Ministral 3 14B (14B).
Related guides & benchmarks
More local AI guides
- How Much RAM (or VRAM) Do You Need for a Local LLM?The model-size-to-memory matrix: what each VRAM and RAM tier actually runs.
- Best LLM for MacBook (Apple Silicon)Unified-memory Macs run bigger models per dollar. Picks by RAM tier, M1 to M5.
- Local AI image generator on MacCompare image models by RAM and app.
- Local image generation on MacImage models and apps by Mac RAM.
Browse all NVIDIA GPUs for AI
Real-world calibration
Have this hardware? Share a measured run.
Measure a fixed Ollama reference model on your machine. This separate, opt-in contribution does not change ModelFit's third-party SWE-Bench leaderboard; results appear on the measured-speed leaderboard after the next site update.
$ npx -y @wecko-ai/modelfit bench --submit --cleanup
Want personalized recommendations?
Use our interactive wizard to compare models across Apple Silicon and NVIDIA GPUs.