GPT OSS 120B Eagle3 Short Context — Hardware Requirements & GPU Compatibility
Chat
GPT OSS 120B Eagle3 Short Context is a 120B-parameter open language model from NVIDIA in the GPT-OSS family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 72.30 GB of VRAM — see which GPUs and Macs can run it below.
57.6K downloads
18 likesSpecifications
- Publisher
- NVIDIA
- Family
- GPT-OSS
- Parameters
- 120B
- Architecture
- LlamaForCausalLMEagle3
- Context Length
- 131,072 tokens
- Vocabulary Size
- 201,088
- Release Date
- 2025-10-06
- License
- Other
Get Started
HuggingFace
Run in cloud
Fits on RTX PRO 6000 (96 GB) (23 GB headroom) · Q4_K_M
- Generation speed
- ~16 tok/s
- generation speed
- Cost per 1M output tokens
- $20.78
- per 1M output tokens
How Much VRAM Does GPT OSS 120B Eagle3 Short Context Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 51.3 GB | 51.5 GB | 51.00 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 58.8 GB | 59.0 GB | 58.50 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 72.3 GB | 72.5 GB | 72.00 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 85.8 GB | 86.0 GB | 85.50 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 99.3 GB | 99.5 GB | 99.00 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 120.3 GB | 120.5 GB | 120.00 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 240.3 GB | 240.5 GB | 240.00 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run GPT OSS 120B Eagle3 Short Context?
Q4_K_M · 72.3 GBGPT OSS 120B Eagle3 Short Context (Q4_K_M) requires 72.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 94+ GB is recommended. Using the full 131K context window can add up to 0.2 GB, bringing total usage to 72.5 GB. No consumer GPU has enough memory.
Rent an NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition (96 GB) from $1.20/hr.
Which Devices Can Run GPT OSS 120B Eagle3 Short Context?
Q4_K_M · 72.3 GB18 devices with unified memory can run GPT OSS 120B Eagle3 Short Context, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does GPT OSS 120B Eagle3 Short Context need?
GPT OSS 120B Eagle3 Short Context requires 72.3 GB of VRAM at Q4_K_M, or 240.3 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 120B × 4.8 bits ÷ 8 = 72 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 0.5 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M72.3 GBQ4_K_M + full context72.5 GB- Can NVIDIA GeForce RTX 5090 run GPT OSS 120B Eagle3 Short Context?
No — GPT OSS 120B Eagle3 Short Context requires at least 51.3 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for GPT OSS 120B Eagle3 Short Context?
For GPT OSS 120B Eagle3 Short Context, Q4_K_M (72.3 GB) offers the best balance of quality and VRAM usage. Q5_K_M (85.8 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 51.3 GB.
VRAM requirement by quantization
Q2_K51.3 GBQ4_K_M ★72.3 GBQ5_K_M85.8 GBQ6_K99.3 GBQ8_0120.3 GBBF16240.3 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run GPT OSS 120B Eagle3 Short Context on a Mac?
Yes, but only at lower quantizations. The smallest Mac that can run GPT OSS 120B Eagle3 Short Context is Mac Studio M4 Max (64 GB) at Q2_K; 9 of the 39 Macs we list can run it at some quantization. For Q4_K_M (72.3 GB) you need a Mac with more unified memory.
- Can I run GPT OSS 120B Eagle3 Short Context locally?
Yes — GPT OSS 120B Eagle3 Short Context can run locally on consumer hardware. At Q4_K_M quantization it needs 72.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is GPT OSS 120B Eagle3 Short Context?
At Q4_K_M, GPT OSS 120B Eagle3 Short Context can reach ~66 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 72.3 × 0.65 = ~72 tok/s
Estimated speed at Q4_K_M (72.3 GB)
~72 tok/s~72 tok/s~66 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of GPT OSS 120B Eagle3 Short Context?
At Q4_K_M, the download is about 72.00 GB. The full-precision BF16 version is 240.00 GB. The smallest option (Q2_K) is 51.00 GB.
- Which GPUs can run GPT OSS 120B Eagle3 Short Context?
No single consumer GPU has enough VRAM to run GPT OSS 120B Eagle3 Short Context at Q4_K_M (72.3 GB). Multi-GPU or professional hardware is required.
- Which devices can run GPT OSS 120B Eagle3 Short Context?
18 devices with unified memory can run GPT OSS 120B Eagle3 Short Context at Q4_K_M (72.3 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.