Skip to content

VRAM reference

gpt-oss-120b on an H100 SXM

Yes, you can fine-tune gpt-oss-120b on one H100 SXM (80 GB) with QLoRA. 4-bit inference: yes, 65 GB of weights, room for 128K tokens of context or 43 concurrent 4K-token sequences.

By Will Schulz · Checked 15 November 2026 · Prices as of November 2026

Verdict by method

Fine-tuningMemory at 2K tokensOne H100 SXM?Longest sequence (batch 1)Largest batch at 2KLargest LoRA rank
QLoRA (4-bit base)66 GBYes4K tokens2256
LoRA (16-bit base)238 GBNo———
Full fine-tuning1,873 GBNo——n/a
InferenceMemory at 8KOne H100 SXM?Longest contextConcurrent 4K sequences
16-bit (BF16/FP16)234 GBNo——
8-bit117 GBNo——
4-bit66 GBYes128K tokens43
  • QLoRA: yes, about 66 GB at 2K tokens, batch 1, rank 16; up to 4K-token sequences at batch 1 or batch 2 at 2K, LoRA rank up to 256.
  • LoRA: no, it needs about 238 GB at 2K tokens, more than the 80 GB available.
  • Full fine-tuning: no, it needs about 1,873 GB at 2K tokens, more than the 80 GB available.

Where the memory goes

At 2,048 tokens per sequence, batch 1, LoRA rank 16, gradient checkpointing on
MethodWeightsTraining stateActivationsTotalOn one H100 SXM80 GB GPUs needed
QLoRA (4-bit base)62 GB0.2 GB4.0 GB66 GBFits1
LoRA (16-bit base)234 GB0.2 GB4.0 GB238 GBDoesn't fit4
Full fine-tuning234 GB1,636 GB4.0 GB1,873 GBDoesn't fit27
One sequence, fp16 KV cache
PrecisionWeightsKV cache at 8KTotalAt 128K contextOn one H100 SXM
16-bit (BF16/FP16)234 GB0.3 GB234 GB238 GBDoesn't fit
8-bit117 GB0.3 GB117 GB122 GBDoesn't fit
4-bit65 GB0.3 GB66 GB70 GBFits

The cheapest way to run it

Renting an H100 SXM costs $4.39 an hour on Runpod Secure Cloud ($2.69 on Runpod Community Cloud). QLoRA on it processes about 15,126 tokens a second by our estimate, so 10 million training tokens take 11 minutes and cost about $0.81.

Job (default settings)MemoryCheapest rental that fitsPer hour
QLoRA fine-tuning66 GBA100 80GB$2.19
LoRA fine-tuning238 GB6 × L40S$6.54
4-bit inference66 GBA100 80GB$2.19
16-bit inference234 GB6 × L40S$6.54

On-demand rates seen on 15 November 2026: Runpod Secure Cloud, Lambda for the A100 40GB. Consumer cards count as single GPUs only; data-centre GPUs up to eight per node. Kojen's GPU training can launch the H100 SXM on Runpod, Vast.ai or Lambda, or pick the cheapest GPU in stock for you.

Try other settings

JobMemoryH100 SXM (80 GB)Smallest single GPU
QLoRA (4-bit base)2K tokens × batch 1, rank 1666 GBFitsA100 80GB (80 GB)
LoRA (16-bit base)2K tokens × batch 1, rank 16238 GB4 GPUsNone: needs several
Full fine-tuning2K tokens × batch 11,873 GB27 GPUsNone: needs several
Inference, 16-bit (BF16/FP16)8K-token context × 1 sequence234 GB4 GPUsNone: needs several
Inference, 8-bit8K-token context × 1 sequence117 GB2 GPUsH200 (141 GB)
Inference, 4-bit8K-token context × 1 sequence66 GBFitsA100 80GB (80 GB)

A job fits when the estimate is within 90% of the card's memory. Training assumes gradient checkpointing and FlashAttention; multi-GPU counts assume the memory splits evenly (FSDP, ZeRO-3 or tensor parallelism).

How we estimate it

Every figure comes from the model's published architecture (layers, hidden size, attention and KV heads, vocabulary) rather than a rule of thumb, using the same functions as the calculator above. Sizes are in GB (10⁹ bytes).

  • Full fine-tuning: 16 bytes per parameter for mixed-precision Adam (bf16 weights and gradients, fp32 master weights and two moments), as in the ZeRO paper.
  • LoRA: frozen bf16 weights (2 bytes per parameter) plus 16 bytes per adapter parameter, rank 16 on every linear layer. For mixture-of-experts models, adapters go on attention only and the experts stay frozen.
  • QLoRA: NF4 weights with double quantisation (4.127 bits per parameter); embeddings and the output head stay in bf16, as bitsandbytes leaves them.
  • Activations: gradient checkpointing and FlashAttention. Each layer's bf16 input is kept, one layer is recomputed at a time, and the output logits take 8 bytes per vocabulary entry per token (fp32 values and gradients). Chunked cross-entropy, as in Unsloth or Liger kernels, cuts that last term.
  • Inference: 2, 1 or about 0.56 bytes per weight (4-bit with group-wise scales), plus an fp16 KV cache of 2 × layers × KV heads × head dim × 2 bytes per token; sliding-window layers only cache their window.
  • Fits means the estimate is within 90% of the card's listed memory; the rest covers the CUDA context, kernels and fragmentation. Multi-GPU counts assume memory splits evenly.

Speed estimates use H100 SXM's dense BF16 peak of 989 TFLOPS, about 4 FLOPs per active parameter per token for LoRA and 40% utilisation; see fine-tuning and training costs for the method.

Frequently asked questions

Can I fine-tune gpt-oss-120b on an H100 SXM?
QLoRA: yes, about 66 GB at 2K tokens, batch 1, rank 16; up to 4K-token sequences at batch 1 or batch 2 at 2K, LoRA rank up to 256. LoRA: no, it needs about 238 GB at 2K tokens, more than the 80 GB available. Full fine-tuning: no, it needs about 1,873 GB at 2K tokens, more than the 80 GB available.
Can I run gpt-oss-120b on an H100 SXM?
16-bit (BF16/FP16) inference: no, the weights alone are 234 GB. 8-bit inference: no, the weights alone are 117 GB. 4-bit inference: yes, 65 GB of weights, room for 128K tokens of context or 43 concurrent 4K-token sequences.
What does fine-tuning gpt-oss-120b on an H100 SXM cost?
With QLoRA at our planning rate of 40% utilisation, about 11 minutes for 10 million training tokens, around $0.81 at $4.39 an hour (Runpod Secure Cloud, November 2026).

Sources

  1. [1]Hugging Face. openai/gpt-oss-120b config.json
  2. [2]OpenAI. openai/gpt-oss-120b model card
  3. [3]OpenAI. gpt-oss-120b & gpt-oss-20b Model Card (arXiv:2508.10925)
  4. [4]NVIDIA. H100 SXM specifications
  5. [5]Runpod. GPU pricing (updated 12 November 2026)
  6. [6]Lambda. GPU cloud pricing
  7. [7]Dettmers et al., 2023. QLoRA: Efficient Finetuning of Quantized LLMs (arXiv:2305.14314)
  8. [8]Hu et al., 2021. LoRA: Low-Rank Adaptation of Large Language Models (arXiv:2106.09685)
  9. [9]Rajbhandari et al., 2019. ZeRO: Memory Optimizations Toward Training Trillion Parameter Models (arXiv:1910.02054)
  10. [10]Korthikanti et al., 2022. Reducing Activation Recomputation in Large Transformer Models (arXiv:2205.05198)

Measure before you rent the GPU.

Prompt tuning and model search in Kojen run on hosted models against your own test cases, so you know whether fine-tuning gpt-oss-120b is worth the GPU time.

Start training free