Skip to content

Best GPU for gpt-oss-20b Locally

Real-time prices and hardware recommendations updated for August 2026.

20B
20B
dense

gpt-oss-20b is a dense model: all 20B parameters activate on every token, so generation speed is bound by how fast your card can stream the full weights.

To run gpt-oss-20b locally you need roughly 14.1 GB of VRAM at Q4_K_M quantization with a 32k token context. The best-value card that fits is the GeForce RTX 5060 Ti 16GB (16 GB), which should generate around 12 tokens per second.

Adjust Context Length

Slide to popular sizes or type any value manually.

k tokens
8k
16k
32k
64k
128k
256k
Budget EntryQ3_K_M quant
8.6 GB
2.6 GB
Total VRAM:11.2 GB

Recommended Hardware

Arc B580
306 tok/sprefill
13 tok/sgeneration
CAD 429.99·12GB VRAM
View Card
GeForce RTX 4070
339 tok/sprefill
14 tok/sgeneration
CAD 1019.99·12GB VRAM
View Card

Q3 weights (~8.6GB) plus 32k KV cache reach ~11GB. 12GB cards cover the full context window with headroom.

Balanced Sweet SpotQ4_K_M quant
11.5 GB
2.6 GB
Total VRAM:14.1 GB

Recommended Hardware

GeForce RTX 5060 Ti 16GB
345 tok/sprefill
12 tok/sgeneration
CAD 949.99·16GB VRAM
View Card
GeForce RTX 4060 Ti 16GB
194 tok/sprefill
7 tok/sgeneration
CAD 1090·16GB VRAM
View Card

Q4 weights (~11.5GB) plus 32k KV cache reach ~14GB. 16GB cards are the ideal mainstream setup.

Near LosslessQ8_0 quant
23 GB
2.6 GB
Total VRAM:25.6 GB

Recommended Hardware

RTX PRO 4500 Blackwell
592 tok/sprefill
14 tok/sgeneration
CAD 5499.99·32GB VRAM
View Card
GeForce RTX 5090
1380 tok/sprefill
29 tok/sgeneration
CAD 5999·32GB VRAM
View Card
RTX A6000
294 tok/sprefill
8 tok/sgeneration
CAD 11399·48GB VRAM
View Card

Q8 weights (~23GB) plus 32k KV cache exceed 24GB. 32GB+ cards deliver near-lossless precision without VRAM constraint.

Other models with the same VRAM requirement

Because gpt-oss-20b's weights fit a 16 GB card, other models of a similar size run on the same GPU. Generation speed varies — mixture-of-experts models are faster, dense models slower — but any of these load in the same VRAM:

InternLM2.5-20B20BCodestral 22B22.2BDiffusionGemma 26B-A4B25.2B

Optimizing Setup for gpt-oss-20b

Quantization Recommendations

For daily coding and reasoning tasks, Q4_K_M (4-bit quantization) offers the best balance of quality and memory efficiency — it reduces memory requirements by over 70% with minimal quality loss compared to FP16. Q8 and higher presets preserve more fidelity at the cost of significantly higher VRAM usage, which may force layer offloading and hurt throughput.

Recommended Local Software

We recommend using Ollama as the primary runner for local inference due to its automated GPU model splitting and context cache optimizations. For advanced fine-tuning or quantization splits, llama.cpp with Flash Attention compiled natively provides the best granular control.

Running gpt-oss-20b locally — FAQ

How much VRAM do I need to run gpt-oss-20b?

At a 32k context with KV cache quantization on, gpt-oss-20b needs about 14.1 GB of VRAM at Q4_K_M — the quantization most people should use. Dropping to Q3_K_M brings that down to roughly 11.2 GB at some quality cost, while Q8_0 needs about 25.6 GB for the best quality this model can give.

What size graphics card does gpt-oss-20b fit on?

gpt-oss-20b needs about 14.1 GB at Q4_K_M, so a 16 GB card is the smallest common size that holds it entirely in VRAM. Anything smaller has to offload layers to system RAM, which typically costs you most of your generation speed.

Which quantization should I use for gpt-oss-20b?

Use Q4_K_M unless you have VRAM to spare. It needs about 14.1 GB and loses very little quality against full precision. Q8_0 needs about 25.6 GB for a quality gain most people cannot detect in everyday coding and chat. Spend spare VRAM on a longer context instead.

How does context length affect the VRAM gpt-oss-20b needs?

Model weights are fixed, but the KV cache grows linearly with context. For gpt-oss-20b at a 32k context the cache is about 2.6 GB; doubling to 64k takes it to roughly 5.1 GB. Turning KV cache quantization off doubles those figures again.

Can the same GPU run other models similar to gpt-oss-20b?

Yes. gpt-oss-20b needs about 14.1 GB at Q4_K_M, and any model whose weights fit the same card runs on it — including InternLM2.5-20B (20B), Codestral 22B (22.2B), DiffusionGemma 26B-A4B (25.2B). The weights fit the same GPU; generation speed varies (mixture-of-experts models are faster, dense models slower).

How token speeds are estimated

Two metrics are shown per GPU: Read tok/s (how fast the model ingests your prompt) and Decode tok/s (how fast it streams tokens back). They model fundamentally different bottlenecks.

📖

Read (Prefill)

The prompt is processed in one parallel pass. This is compute-bound: it saturates the GPU's tensor cores.

read tok/s ≈ TFLOPS × readFactor × 400 ÷ activeParams

Decode (Generation)

Each new token requires loading the entire model's active weights from VRAM. This is memory-bandwidth-bound: the GPU stalls waiting for data, not computing.

decode tok/s ≈ bandwidth × decodeFactor ÷ (weights + kv_cache)

Weights = (activeParams × bits ÷ 8) × 1.15 overhead. KV cache per step = activeParams × multiplier × contextK.

Architecture utilization factors

Architecture
Decode
Read
Blackwell, Xe2
0.45
0.55
Ada Lovelace, RDNA 4, Battlemage
0.38
0.48
Ampere, Turing, RDNA 3, Xe-HPG
0.28
0.38
Volta, RDNA 1/2
0.2
0.25
Pre-tensor-core (Pascal, Maxwell, Kepler, GCN, Alchemist)
0.12
0.15

Left: decode factor — Right: read factor

Data sources

TFLOPS and memory bandwidth are read from the GPU database. When missing, bandwidth falls back to a hardcoded dictionary.

Limitations

These are analytical estimates, not benchmark results. Use them as a relative comparison, not an absolute performance guarantee.