Can I run Nemotron 3.5 Parse locally?
Nemotron 3.5 Parse by nvidia has 631M parameters. At 4-bit with an 8K context it needs about 1.1 GB of GPU memory. It fits on 65 of 65 GPUs and Macs we track. See all models that fit in 8 GB of VRAM.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from SkyContact/Nemotron-3.5-Parse-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx | 8K ctx |
|---|---|---|---|
| 2-bit (Q2_K) | rough | 0.8 GB | 0.9 GB |
| 3-bit (Q3_K_M) | usable | 0.9 GB | 1.0 GB |
| 4-bit (Q4_K_M) | good, most popular | 1.0 GB | 1.1 GB |
| 5-bit (Q5_K_M) | very good | 1.0 GB | 1.1 GB |
| 6-bit (Q6_K) | near lossless | 1.1 GB | 1.2 GB |
| 8-bit (Q8_0) • | effectively lossless | 1.4 GB | 1.5 GB |
| 16-bit (F16/BF16) • | original weights | 1.8 GB | 1.9 GB |
Which GPUs and Macs run Nemotron 3.5 Parse?
Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).
| Hardware | Memory | Fits? | Best quant | Needs | Max tok/s (est.) | Details |
|---|---|---|---|---|---|---|
| RTX 3060 12GB | 12 GB | Fits | F16 | 1.9 GB | 275 | details |
| RTX 4060 Ti 16GB | 16 GB | Fits | F16 | 1.9 GB | 220 | details |
| RTX 3090 | 24 GB | Fits | F16 | 1.9 GB | 716 | details |
| RTX 4090 | 24 GB | Fits | F16 | 1.9 GB | 771 | details |
| RTX 5090 | 32 GB | Fits | F16 | 1.9 GB | 1371 | details |
| RTX 5070 Ti | 16 GB | Fits | F16 | 1.9 GB | 686 | details |
| RX 7900 XTX | 24 GB | Fits | F16 | 1.9 GB | 735 | details |
| Mac M4 Pro 48GB | 48 GB | Fits | F16 | 1.9 GB | 209 | details |
| Mac M4 Max 128GB | 128 GB | Fits | F16 | 1.9 GB | 418 | details |
| Mac M3 Ultra 512GB | 512 GB | Fits | F16 | 1.9 GB | 627 | details |
| DGX Spark | 128 GB | Fits | F16 | 1.9 GB | 209 | details |
| RTX 4070 | 12 GB | Fits | F16 | 1.9 GB | 386 | details |
| RTX 5060 Ti 16GB | 16 GB | Fits | F16 | 1.9 GB | 343 | details |
| RTX 4060 | 8 GB | Fits | F16 | 1.9 GB | 208 | details |
| Arc B580 | 12 GB | Fits | F16 | 1.9 GB | 349 | details |
| RTX 3060 Ti | 8 GB | Fits | F16 | 1.9 GB | 343 | details |
| RTX 3070 | 8 GB | Fits | F16 | 1.9 GB | 343 | details |
| RTX 3080 10GB | 10 GB | Fits | F16 | 1.9 GB | 581 | details |
| RTX 3080 12GB | 12 GB | Fits | F16 | 1.9 GB | 698 | details |
| RTX 3090 Ti | 24 GB | Fits | F16 | 1.9 GB | 771 | details |
| RTX 4060 Ti 8GB | 8 GB | Fits | F16 | 1.9 GB | 220 | details |
| RTX 4070 Super | 12 GB | Fits | F16 | 1.9 GB | 386 | details |
| RTX 4070 Ti | 12 GB | Fits | F16 | 1.9 GB | 386 | details |
| RTX 4070 Ti Super | 16 GB | Fits | F16 | 1.9 GB | 514 | details |
| RTX 4080 | 16 GB | Fits | F16 | 1.9 GB | 549 | details |
| RTX 4080 Super | 16 GB | Fits | F16 | 1.9 GB | 563 | details |
| RTX 5060 | 8 GB | Fits | F16 | 1.9 GB | 343 | details |
| RTX 5070 | 12 GB | Fits | F16 | 1.9 GB | 514 | details |
| RTX 5080 | 16 GB | Fits | F16 | 1.9 GB | 735 | details |
| 2x RTX 3090 | 2×24 GB | Fits | F16 | 1.9 GB | 716 | details |
| 2x RTX 4090 | 2×24 GB | Fits | F16 | 1.9 GB | 771 | details |
| 2x RTX 5090 | 2×32 GB | Fits | F16 | 1.9 GB | 1371 | details |
| RTX A6000 | 48 GB | Fits | F16 | 1.9 GB | 588 | details |
| RTX 6000 Ada | 48 GB | Fits | F16 | 1.9 GB | 735 | details |
| RTX PRO 6000 Blackwell | 96 GB | Fits | F16 | 1.9 GB | 1371 | details |
| L40S | 48 GB | Fits | F16 | 1.9 GB | 661 | details |
| A100 40GB | 40 GB | Fits | F16 | 1.9 GB | 1190 | details |
| A100 80GB | 80 GB | Fits | F16 | 1.9 GB | 1560 | details |
| H100 PCIe | 80 GB | Fits | F16 | 1.9 GB | 1530 | details |
| H100 SXM | 80 GB | Fits | F16 | 1.9 GB | 2563 | details |
| H200 | 141 GB | Fits | F16 | 1.9 GB | 3673 | details |
| RX 7600 | 8 GB | Fits | F16 | 1.9 GB | 220 | details |
| RX 7700 XT | 12 GB | Fits | F16 | 1.9 GB | 331 | details |
| RX 7800 XT | 16 GB | Fits | F16 | 1.9 GB | 477 | details |
| RX 7900 GRE | 16 GB | Fits | F16 | 1.9 GB | 441 | details |
| RX 7900 XT | 20 GB | Fits | F16 | 1.9 GB | 612 | details |
| RX 9070 | 16 GB | Fits | F16 | 1.9 GB | 490 | details |
| RX 9070 XT | 16 GB | Fits | F16 | 1.9 GB | 490 | details |
| Ryzen AI Max+ 395 128GB | 128 GB | Fits | F16 | 1.9 GB | 196 | details |
| Arc A770 16GB | 16 GB | Fits | F16 | 1.9 GB | 428 | details |
| Mac M1 16GB | 16 GB | Fits | F16 | 1.9 GB | 52 | details |
| Mac M2 24GB | 24 GB | Fits | F16 | 1.9 GB | 77 | details |
| Mac M3 24GB | 24 GB | Fits | F16 | 1.9 GB | 77 | details |
| Mac M4 16GB | 16 GB | Fits | F16 | 1.9 GB | 92 | details |
| Mac M4 32GB | 32 GB | Fits | F16 | 1.9 GB | 92 | details |
| Mac M1 Pro 32GB | 32 GB | Fits | F16 | 1.9 GB | 153 | details |
| Mac M3 Pro 36GB | 36 GB | Fits | F16 | 1.9 GB | 115 | details |
| Mac M4 Pro 24GB | 24 GB | Fits | F16 | 1.9 GB | 209 | details |
| Mac M4 Pro 64GB | 64 GB | Fits | F16 | 1.9 GB | 209 | details |
| Mac M1 Max 64GB | 64 GB | Fits | F16 | 1.9 GB | 306 | details |
| Mac M2 Max 96GB | 96 GB | Fits | F16 | 1.9 GB | 306 | details |
| Mac M3 Max 128GB | 128 GB | Fits | F16 | 1.9 GB | 306 | details |
| Mac M4 Max 64GB | 64 GB | Fits | F16 | 1.9 GB | 418 | details |
| Mac M2 Ultra 192GB | 192 GB | Fits | F16 | 1.9 GB | 612 | details |
| Mac M3 Ultra 256GB | 256 GB | Fits | F16 | 1.9 GB | 627 | details |
Questions
How much VRAM does Nemotron 3.5 Parse need?
About 1.1 GB at 4-bit (Q4_K_M) with an 8K context: 0.4 GB of weights (estimated), 0.2 GB of KV cache and 0.5 GB of runtime overhead. At 8-bit it needs about 1.5 GB.
What is the smallest GPU that runs Nemotron 3.5 Parse?
At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 4060 (8 GB).
Can I run Nemotron 3.5 Parse on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M1 16GB or larger, using the default macOS GPU memory limit.
Similar models
Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.
Cosmos Reason2 2B
2.4B · 2.8 GB at 4-bitGOT OCR 2.0 HF
561M · 1.8 GB at 4-bitGOT OCR2.0
716M · 1.8 GB at 4-bitQwen3 0.6B
752M · 2.0 GB at 4-bitSmolVLM2 500M Video Instruct
507M · 1.1 GB at 4-bitSmolVLM 500M Instruct
507M · 1.1 GB at 4-bitEmbed this
Free badge and "Will it run on my GPU?" widget for model cards, READMEs and blogs. No cookies, no tracking. All options.
Copy a snippet
Markdown badge
[](https://runsonmy.com/model/nemotron-3-5-parse/) Widget (script)
<div class="runsonmy-widget" data-model="nemotron-3-5-parse"><a href="https://runsonmy.com/model/nemotron-3-5-parse/">Will Nemotron 3.5 Parse run on my GPU? Check on RunsOnMy</a></div>
<script async src="https://runsonmy.com/embed.js"></script> Widget (iframe)
<iframe src="https://runsonmy.com/embed/m/nemotron-3-5-parse/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will Nemotron 3.5 Parse run on my GPU? (RunsOnMy)"></iframe> Model facts
| Hugging Face repo | nvidia/Nemotron-3.5-Parse |
| Parameters | 630,800,504 (631M) |
| Layers / hidden size | 10 / 1024 |
| Attention | GQA; 16 heads, 8 KV heads, head dim 64 |
| KV cache per token (FP16) | 20.0 KiB |
| Max context | 16,384 tokens |
| License | openmdw-1.1 |
| Released on HF | Sep 3, 2026 |
| Downloads (30d) / likes | 26,121 / 169 |
Sources: Hugging Face model API · config.json (nvidia/Nemotron-3.5-Parse) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.