NVIDIA · workstation

RTX 5880 Ada Generation

RTX 5880 Ada Generation has 48 GB of VRAM at 960 GB/s — about 44.64 GiB usable after driver and compositor overhead. 1978 of 2118 indexed models fit at 64K context with f16 KV.

Spec sheet· bandwidth, theoreticalFrom the file· fit from summed bytesPredicted· speed
Memory
48 GB
GDDR6
Bandwidth
960 GB/s
384-bit bus
Tensor FP16
277 TF
dense
TDP
285 W
$6999 MSRP
Context4K8K16K32K64K128K
KV cachef16q8_0q4_0quantizing the KV cache is a ~2× lever on the dominant term at long context
text 1693vision language 181image 2audio asr 39audio tts 21video 16embedding 26

What fits at 64K context

largest quantization that fits, per model · 1978 of 2118 indexed
ModelBest quantParamsWeights●KV●Total in memory◐Headroom◐tok/s◐
codegeex4-all-9bIQ2_S9.4B3.51 GiB40.00 GiB44.56 GiB0.08 GiB13±22%
glm-4-9b-chatIQ2_S9.4B3.51 GiB40.00 GiB44.55 GiB0.09 GiB13±22%
Huihui-Qwen3-Coder-Next-abliteratedMoEIQ4_NL79.7B42.04 GiB1.50 GiB44.53 GiB0.11 GiB63±37%
Rocinante-XL-16B-v1BF1616.1B29.93 GiB13.50 GiB44.48 GiB0.16 GiB13±22%
Melody1437-27BQ5_K_M27.8B39.34 GiB4.00 GiB44.40 GiB0.24 GiB13±22%
IQuest-Coder-V1-40B-InstructI1-Q4_139.8B23.24 GiB20.00 GiB44.34 GiB0.30 GiB13±22%
Hypernova-60B-2605MoEI1-Q5_K_M58.7B41.29 GiB2.02 GiB44.30 GiB0.34 GiB48±37%
Apertus-70B-Instruct-2509UD-IQ2_M70.6B23.12 GiB20.00 GiB44.30 GiB0.34 GiB13±22%
NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16MoEQ4_K_S75.4B43.15 GiB0.00 GiB44.22 GiB0.42 GiB111±37%
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTPQ5_K_M27.8B39.03 GiB4.00 GiB44.10 GiB0.54 GiB13±22%
GLM-4.5VMoEI1-IQ1_S108B31.56 GiB11.50 GiB44.09 GiB0.55 GiB20±37%
llm-surgery-dark-arts-gpt-oss-60b-96a12MoEI1-Q5_K_S60.9B41.56 GiB1.52 GiB44.07 GiB0.57 GiB35±37%
Qwen3.5-122B-A10B-hereticMoEI1-Q2_K123B41.52 GiB1.50 GiB44.04 GiB0.60 GiB59±37%
Gemma-4-31B-Isometry-RPQ8_032.7B31.79 GiB11.17 GiB44.04 GiB0.60 GiB13±22%
Prosopon-31BQ8_032.7B31.79 GiB11.17 GiB44.04 GiB0.60 GiB13±22%
Gemma-4-Novelist-Eclipse-31BQ8_032.7B31.79 GiB11.17 GiB44.04 GiB0.60 GiB13±22%
Giftige-Blume-31B-v1-StyleSwapQ8_032.7B31.79 GiB11.17 GiB44.04 GiB0.60 GiB13±22%
G4-MeroMero-31B-StyleSwapQ8_032.7B31.79 GiB11.17 GiB44.04 GiB0.60 GiB13±22%
Gemma-4-31B-StyleTune-heretic-araQ8_032.7B31.79 GiB11.17 GiB44.04 GiB0.60 GiB13±22%
Pantheon-Reasoning-31B-1.1Q8_032.7B31.79 GiB11.17 GiB44.04 GiB0.60 GiB13±22%
Gemma-4-31B-StyleTuneQ8_032.7B31.79 GiB11.17 GiB44.04 GiB0.60 GiB13±22%
Barcenas-StyleTune-31B-FableQ8_032.1B31.79 GiB11.17 GiB44.04 GiB0.60 GiB13±22%
ALIA-40b-fc-2606I1-Q6_K40.4B30.90 GiB12.00 GiB44.01 GiB0.63 GiB13±22%
ALIA-40b-instruct-2606I1-Q6_K40.4B30.90 GiB12.00 GiB44.01 GiB0.63 GiB13±22%
Qwen3.5-122B-A10BMoEIQ2_M125B41.39 GiB1.50 GiB43.92 GiB0.72 GiB59±37%
Maenad-70BI1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
DeepSeek-R1-Distill-Llama-70B-Uncensored-v2-Unbiased-ReasonerI1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
Rombos-LLM-70b-Llama-3.3I1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
L3.3-Electra-R1-70bI1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
Latxa-Llama-3.1-70B-Instruct-v2I1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
Llama-3.3_70_b_uncensored_continuedI1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
Llama-3.3-70B-Instruct-abliteratedI1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
grok-oss-Revenant-70BI1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
Llama-3.1-Nemotron-70B-Instruct-HFI1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
L3.3-70B-Euryale-v2.3I1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
Hermes-4-70B-hereticI1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
Llama-3.1-70BQ2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
Golem-70B-v1bI1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
DeepSeek-R1-Distill-Llama-70B-abliteratedI1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
DeepSeek-R1-Distill-Llama-70B-hereticI1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
Legion-V2.1-LLaMa-70BI1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
Assistant_Pepe_70BI1-Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
Athene-70BQ2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
Hermes-3-Llama-3.1-70BQ2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
L3.3-70B-Magnum-DiamondQ2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
Meta-Llama-3-70B-Instruct-abliterated-v3.5Q2_K_S70.6B22.79 GiB20.00 GiB43.92 GiB0.72 GiB13±22%
Janus-Pro-7BF167.4B12.88 GiB30.00 GiB43.90 GiB0.74 GiB13±22%
c4ai-command-r-plus-08-2024IQ2_XXS104B26.65 GiB16.00 GiB43.83 GiB0.81 GiB13±22%
DeepSeek-R1-Distill-Llama-70BUD-IQ2_M70.6B22.70 GiB20.00 GiB43.82 GiB0.82 GiB13±22%
Mistral-Small-4-119B-2603MoEUD-IQ3_S119B41.36 GiB1.41 GiB43.80 GiB0.84 GiB60±37%
Hermes-4-70BUD-IQ2_M70.6B22.63 GiB20.00 GiB43.75 GiB0.89 GiB13±22%
Llama-3.3-70B-InstructUD-IQ2_M70.6B22.63 GiB20.00 GiB43.75 GiB0.89 GiB13±22%
Hunyuan-A13B-InstructMoEIQ3_M80.4B34.72 GiB8.00 GiB43.71 GiB0.93 GiB13±22%
Llama-4-Scout-17B-16E-InstructMoEKV unresolvedIQ2_XS109B30.68 GiB12.00 GiB43.71 GiB0.93 GiB20±37%
deepseek-llm-67b-chatI1-IQ2_XS67.4B18.78 GiB23.75 GiB43.63 GiB1.01 GiB13±22%
deepseek-llm-67b-baseI1-IQ2_XS67.4B18.78 GiB23.75 GiB43.63 GiB1.01 GiB13±22%
openbuddy-deepseek-67b-v15.3-4kI1-IQ2_XS67.4B18.78 GiB23.75 GiB43.63 GiB1.01 GiB13±22%
L3.3-70B-Magnum-v4-SEIQ2_M70.6B22.46 GiB20.00 GiB43.59 GiB1.05 GiB13±22%
Anubis-70B-v1.2IQ2_M70.6B22.46 GiB20.00 GiB43.59 GiB1.05 GiB13±22%
Tess-R1-Limerick-Llama-3.1-70BIQ2_M70.6B22.46 GiB20.00 GiB43.59 GiB1.05 GiB13±22%
●From the file◐Predictedwhat these mean

Speed is modeled, not measured: decode is memory-bandwidth bound, so tokens per second is bytes read per token against achievable bandwidth. Mixture-of-experts models carry a wider band because only the routed experts are read each step, and few have been measured publicly.

Questions people ask

What AI models can a RTX 5880 Ada Generation run?
1978 of 2118 indexed open-weight models fit a RTX 5880 Ada Generation at 65,536 context with f16 KV cache, the largest being codegeex4-all-9b at IQ2_S. That covers text, vision-language, image, video and speech models.
How much usable memory does a RTX 5880 Ada Generation actually have?
Its nameplate is 48 GB, but about 44.64 GiB is available to a model once driver and compositor overhead is accounted for.
Is a RTX 5880 Ada Generation fast for local AI?
Its memory bandwidth is 960 GB/s, and that figure — not teraflops — is what governs token generation speed. Capacity decides what you can run; bandwidth decides how fast it runs.