Hardware

RTX A6000

RTX A6000 has 48 GB GDDR6 and 768 GB/s. See which open models fit, at which quant, and roughly how fast. Figures below use the default memory (48 GB), 32 GB system RAM, and DDR5-5600 for anything that spills. Updated 2026-10-24.

Memory48 GB GDDR6

Bandwidth768 GB/s

Kindgpu

Year2020

48GB GDDR6, 768 GB/s. Source.

RSS for new models on this device

Models that fit

Model	Verdict	Quant	Context	tok/s
Qwen2.5 72B Instruct 72.7B	Tight fit	IQ4_XS	8K	10.0–14
Qwen3 Next 80B A3B Thinking 79.7B	Tight fit	UD-Q4_K_XL	4K	198–270
Qwen3 Next 80B A3B Instruct 79.7B	Tight fit	UD-Q4_K_XL	4K	198–270
Qwen3 Coder Next 79.7B	Tight fit	UD-Q4_K_S	4K	51–70
Mistral Small 4 119B 2603 119B	Tight fit	UD-IQ3_S	8K	51–70
Mistral Medium 3.5 128B 125B	Runs	UD-IQ2_XXS	8K	11–15
Llama 4 Scout 17B 16E Instruct 108B	Tight fit	UD-IQ3_XXS	4K	40–55
Qwen3.5 122B A10B MTP 125B	Tight fit	UD-Q2_K_XL	8K	116–158
Qwen2.5 32B Instruct 32.8B	Runs	Q8_0	8K	11–16
Qwen2.5 Coder 32B Instruct 32.8B	Runs	Q8_0	8K	11–16
DeepSeek R1 Distill Qwen 32B 32.8B	Runs	Q8_0	8K	11–16
Qwen3 32B 32.8B	Tight fit	UD-Q8_K_XL	8K	10–14
Qwen3 VL 32B Instruct 32.8B	Tight fit	UD-Q8_K_XL	8K	10–14
GLM 4 32B 0414 32.6B	Runs	UD-Q8_K_XL	8K	11–14
gemma 4 31B it 30.7B	Runs	UD-Q8_K_XL	8K	9.8–13
GLM 4.6V 107B	Tight fit	UD-Q2_K_XL	4K	40–55
Qwen3.8 27B 27.3B	Runs	UD-Q8_K_L	8K	15–20
Swift Qwen3.8 27B 27.3B	Runs	Q8_0	8K	14–19
gemma 3 27b it 27.0B	Runs	UD-Q8_K_XL	8K	12–16
medgemma 27b text it 27.0B	Runs	UD-Q8_K_XL	8K	12–16
Qwen3.6 27B 26.9B	Runs	UD-Q8_K_XL	8K	12–16
Qwen3.5 27B 26.9B	Runs	UD-Q8_K_XL	8K	12–16
Kwaipilot KAT Coder V2.5 Dev 34.7B	Runs	Q8_0	8K	62–84
Qwen3.8 35B A3B Distill 35.5B	Runs	Q8_0	8K	126–171
Cyber Tiel Coder 35B A3B GGUF MTP 35.5B	Runs	Q8_0 (est.)	8K	126–172
GLM 4.5 Air 110B	Tight fit	UD-IQ2_XXS	8K	40–54
Qwen3.5 35B A3B 34.7B	Runs	Q8_0	8K	126–171
Qwen3.6 35B A3B 34.7B	Runs	UD-Q8_K_XL	8K	121–165
Tiel Coder 35B A3B 34.7B	Runs	UD-Q8_K_XL	8K	121–165
NVIDIA Nemotron 3.5 Lightning 30B A3B 32.9B	Runs	UD-Q8_K_XL	8K	107–146
Devstral Small 2 24B Instruct 2512 23.6B	Runs	UD-Q8_K_XL	8K	14–19
Mistral Small 3.2 24B Instruct 2506 23.6B	Runs	UD-Q8_K_XL	8K	14–19
Magistral Small 2509 23.6B	Runs	UD-Q8_K_XL	8K	14–19
NVIDIA Nemotron 3 Nano Omni 30B A3B Reasoning 31.6B	Runs	UD-Q8_K_XL	8K	111–152
Nemotron 3 Nano 30B A3B 31.6B	Tight fit	UD-Q8_K_XL	8K	99–135
GLM 4.7 Flash 29.9B	Runs	UD-Q8_K_XL	8K	53–72
Qwen3 Coder 30B A3B Instruct 30.5B	Runs	UD-Q8_K_XL	8K	97–133
Qwen3 30B A3B Instruct 2507 30.5B	Runs	UD-Q8_K_XL	8K	97–133
Qwen3 VL 30B A3B Instruct 30.5B	Runs	UD-Q8_K_XL	8K	97–133
Qwen3 30B A3B Thinking 2507 30.5B	Runs	UD-Q8_K_XL	8K	97–133

105 more models in the catalog do not fit this default profile, or ranked below the first 40 that do.

Example: Tight fit fully on your RTX A6000 at IQ4_XS, 8K context, about 10.0–14 tok/s. Weights 37.0 GB plus 2.50 GB of KV cache — 40.2 GB of 45.1 GB usable. Up to 16K context still fits. Weights shown in the verdict use GiB (the same 1024³ counting as GPU memory).