What is the best model the NVIDIA GeForce RTX 5070 can run locally?

Qwen 3.8 27B (UD-Q5_K_M) fits fully in its memory at 32k context and generates at about 19 tok/s, an estimate from its memory bandwidth. 48 of the 113 models we track fit at that context.

Can the NVIDIA GeForce RTX 5070 run DeepSeek V4 Flash?

No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 94 GB at 32k context, more than the NVIDIA GeForce RTX 5070 and system RAM can hold.

NVIDIA GeForce RTX 5070

12 GB · 672 GB/s · 250 W

In short

The NVIDIA GeForce RTX 5070 has 12 GB of GDDR7 memory with 672 GB/s of bandwidth, which sets how fast it generates text. At 32k context it runs 48 of the 113 open models we track fully in memory; the most capable is Qwen 3.8 27B at UD-Q5_K_M, at about 19 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 5070 in Germany is 699 € at eBay; used, it starts at 780 € (asking price).

Updated 15 October 2026. Speeds are estimates; how they are worked out.

Prices

Every retailer we track in Germany, cheapest first. Buy links may earn us a commission.

Retailer	Condition	Price	Stock	Checked	Buy
eBayGIGABYTE GeForce RTX 5070 Eagle OC ICE SFF 12GB GDDR7 RAM 1x HDMI 3x DP Neu OVP	New	699 €+ 5 € delivery	In stock	2 h ago	Buy
eBayASUS Dual GeForce RTX 5070 OC 12GB DUAL-RTX5070-O12G Grafikkarte GDDR7 DP/HDMI	used, asking price	780 €+ 8 € delivery	In stock	2 h ago	Buy
eBayGIGABYTE EAGLE OC SFF GeForce RTX 5070 12GB Grafikkarte Raytracing	used, asking price	800 €	In stock	2 h ago	Buy
eBayGIGABYTE GeForce RTX 5070 GAMING OC 12GB GDDR7 PCIe 5.0 x16 Grafikkarte	New	798 €+ 8 € delivery	In stock	2 h ago	Buy
eBayASUS PRIME GeForce RTX 5070 OC 12GB	New	800 €+ 8 € delivery	In stock	2 h ago	Buy
AmazonASUS Dual GeForce RTX 5070 12GB GDDR7 OC Edition Gaming Graphics Card	New	817 €	In stock	42 min ago	Buy
AmazonMSI GeForce RTX 5070 12G Ventus 2X OC Gaming Graphics Card	New	835 €	In stock	42 min ago	Buy
eBayMSI GeForce RTX 5070 12GB VENTUS 3X OC 12GB GDDR7.	used, asking price	837 €+ 8 € delivery	In stock	2 h ago	Buy
eBayZotac Gaming GeForce RTX 5070 Twin Edge	used, asking price	849 €	In stock	2 h ago	Buy
eBayMSI GeForce RTX 12GB 5070 GAMING TRIO OC WHITE Grafikkarte + ARGB MSI Halter	used, asking price	865 €+ 8 € delivery	In stock	2 h ago	Buy
AmazonASUS Prime GeForce RTX 5070 12GB GDDR7 OC Edition Gaming Graphics Card	New	879 €	In stock	47 min ago	Buy
AmazonPNY GeForce RTX 5070 12GB Triple Fan Graphics Card DLSS 4	New	880 €	In stock	36 min ago	Buy
AmazonGigabyte GeForce RTX 5070 Eagle OC Ice SFF 12G Graphics Card	New	885 €	In stock	36 min ago	Buy
AmazonGIGABYTE GeForce RTX 5070 WINDFORCE SFF 12G Graphics Card	New	891 €	In stock	25 min ago	Buy
AmazonMSI GeForce RTX 5070 12G Shadow 2X OC Gaming Graphics Card	New	900 €	In stock	42 min ago	Buy
AmazonMSI GeForce RTX 5070 12G Gaming Trio OC Gaming Graphics Card	New	904 €	In stock	42 min ago	Buy
AmazonPNY GeForce RTX 5070 12GB ARGB OC Triple Fan Graphics Card DLSS 4	New	913 €	In stock	42 min ago	Buy
AmazonPNY NVIDIA GeForce RTX 5070 Slim Dual Fan 12GB GDDR7 OC Graphics Card	New	916 €	In stock	36 min ago	Buy
eBayASUS GeForce RTX 5070 Dual OC 12GB GDDR7 DLSS4	New	937 €	In stock	2 h ago	Buy
eBayGrafikkarte ASUS Prime GeForce RTX 5070 OC	New	940 €	In stock	2 h ago	Buy
eBayGIGABYTE GeForce RTX 5070 Eagle OC ICE SFF 12GB GDDR7 RAM 1x HDMI 3x DP Neu OVP	New	930 €+ 12 € delivery	In stock	2 h ago	Buy
eBayInno3D Nvidia GeForce RTX 5070 TwinX2 OC WHITE 12GB GDDR7 RAM HDMI 3x DP Neu OVP	New	930 €+ 12 € delivery	In stock	2 h ago	Buy
AmazonASUS Prime GeForce RTX 5070 12GB GDDR7 Gaming Graphics Card	New	949 €	In stock	36 min ago	Buy
eBayMSI GeForce Nvidia RTX 5070 VENTUS 2X OC 12GB GDDR7 HDMI 3x DP	New	940 €+ 12 € delivery	In stock	2 h ago	Buy
eBayASUS Dual GeForce RTX 5070 12GB GDDR7 OC Edition Gaming Grafikkarte	New	955 €	In stock	2 h ago	Buy
eBayPNY Nvidia GeForce RTX 5070 EPIC-X ARGB OC 12GB GDDR7 RAM 1x HDMI 3x DP Neu 19%	New	945 €+ 12 € delivery	In stock	2 h ago	Buy
eBayGIGABYTE GeForce RTX 5070 GAMING OC 12G Grafikkarte	New	960 €	In stock	2 h ago	Buy
eBayGigabyte GeForce RTX 5070 Gaming OC 12 GB GDDR7 PCIe 5.0 x16	New	968 €	In stock	2 h ago	Buy
eBayASUS PRIME GeForce RTX 5070 12GB GDDR7 OC Edition	New	975 €	In stock	2 h ago	Buy
AmazonGigabyte GeForce RTX 5070 WINDFORCE SFF 12G Graphics Card	New	975 €	In stock	36 min ago	Buy
eBayZotac GeForce RTX 5070 Twin Edge OC 12 GB GDDR7 PCIe 5.0 x16	New	980 €	In stock	2 h ago	Buy
AmazonASUS Prime GeForce RTX 5070 12GB GDDR7 White OC Edition Graphics Card	New	993 €	In stock	36 min ago	Buy
AmazonNVIDIA	New	1.000 €	In stock	25 min ago	Buy
eBayASUS PRIME GeForce RTX 5070 12 GB GDDR7 OC Edition Gaming Grafikkarte	New	1.003 €	In stock	2 h ago	Buy
eBayMSI GeForce RTX 5070 Gaming Trio OC 12 GB GDDR7 PCIe 5.0 x16	New	1.013 €	In stock	2 h ago	Buy
AmazonASUS The T1 GeForce RTX 5070 12GB GDDR7 Graphics Card	New	999 €+ 21 € delivery	In stock	36 min ago	Buy
AmazonGigabyte Aorus GeForce RTX 5070 Master 12G Graphics Card	New	1.046 €	In stock	36 min ago	Buy
AmazonASUS ROG Strix GeForce RTX 5070 OC Edition 12GB GDDR7 Gaming Graphics Card	New	1.344 €+ 41 € delivery	In stock	25 min ago	Buy

Used on eBay: median asking price 810 €, most between 790 € and 853 € (8 listings, 2026-10-15).

Price history

Lowest price shown each day over the last 90 days.

Not enough price history yet.

What two of them run

Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.

Model	Quant	Fits	Memory	Max context	Decode @32k	Prefill	Good for
Qwen 3.8 27B Alibaba Qwen	UD-Q5_K_M	fits	21.8 GB	46k80k with q8 cache	19tok/sest.	450 tok/s	chat
Qwen 3.6 27B Alibaba Qwen	Q5_K_M	fits	21.6 GB	49k86k with q8 cache	19tok/sest.	450 tok/s	chat
Gemma 4 31B Google	Q4_K_M	fits	21.6 GB	45k89k with q8 cache	19tok/sest.	401 tok/s	chat
Qwen 3.6 35B-A3B Alibaba Qwen	Q4_K_M	fits	22.7 GB	34k54k with q8 cache	96tok/sest.	3213 tok/s	chat, coding, agents, long documents
Qwen 3.5 27B Alibaba Qwen	Q5_K_M	fits	21.7 GB	48k84k with q8 cache	19tok/sest.	450 tok/s	chat
Gemma 4 26B-A4B Google	UD-Q5_K_M	fits	21.8 GB	71k116k with q8 cache	60tok/sest.	2858 tok/s	chat, coding, agents, long documents
Qwen 3.5 35B-A3B Alibaba Qwen	Q4_K_M	fits	22.5 GB	44k70k with q8 cache	97tok/sest.	3213 tok/s	chat, coding, agents, long documents
GLM 4.7 Flash Z.ai	Q4_K_M	fits	20.0 GB	80k139k with q8 cache	52tok/sest.	1677 tok/s	chat, coding, agents
Devstral Small 2 24B Mistral AI	Q5_K_M	fits	21.9 GB	37k68k with q8 cache	19tok/sest.	475 tok/s	chat
gpt-oss 20B OpenAI	MXFP4	fits	13.3 GB	128k	77tok/sest.	2398 tok/s	chat, coding, agents, long documents
Qwen3 Coder 30B-A3B Alibaba Qwen	Q4_K_M	fits	21.6 GB	44k79k with q8 cache	50tok/sest.	1477 tok/s	chat, coding, agents
Gemma 4 12B Google	Q8_0	fits	13.9 GB	256k	31tok/sest.	1044 tok/s	chat, coding, long documents
Qwen 3.5 9B Alibaba Qwen	Q8_0	fits	11.2 GB	256k	39tok/sest.	1301 tok/s	chat, coding, long documents
Mistral Small 3.2 24B Mistral AI	Q5_K_M	fits	21.9 GB	37k68k with q8 cache	19tok/sest.	475 tok/s	chat
Gemma 3 27B Google	Q5_K_M	fits	22.1 GB	39k74k with q8 cache	19tok/sest.	478 tok/s	chat
Ministral 3 14B Mistral AI	Q8_0	fits	19.7 GB	51k93k with q8 cache	21tok/sest.	722 tok/s	chat, coding
Qwen3 14B Alibaba Qwen	Q8_0	fits	20.9 GB	40k	20tok/sest.	650 tok/s	chat
DeepSeek R1 0528 Qwen3 8B DeepSeek	Q8_0	fits	13.9 GB	92k128k with q8 cache	31tok/sest.	1071 tok/s	chat, coding
Qwen3 8B Alibaba Qwen	Q8_0	fits	13.9 GB	40k	31tok/sest.	1071 tok/s	chat, coding
Phi-4 14B Microsoft	Q8_0	fits	22.0 GB	16k	19tok/sest.	653 tok/s	chat
Qwen 3.5 4B Alibaba Qwen	Q8_0	fits	6.5 GB	256k	74tok/sest.	2433 tok/s	chat, coding, long documents
Ministral 3 8B Mistral AI	Q8_0	fits	13.9 GB	95k173k with q8 cache	31tok/sest.	1035 tok/s	chat, coding
Granite 4.2 8B IBM	Q8_0	fits	15.0 GB	80k128k with q8 cache	28tok/sest.	985 tok/s	chat, coding
Gemma 4 E4B Google	Q8_0	fits	9.8 GB	128k	45tok/sest.	1634 tok/s	chat, coding, long documents
LFM2.5 8B-A1B Liquid AI	Q8_0	fits	11.2 GB	125k	94tok/sest.	5344 tok/s	chat, coding, long documents
Llama 3.1 8B Meta	Q6_K	fits	11.4 GB	118k128k with q8 cache	38tok/sest.	1132 tok/s	chat, coding
Qwen2.5 0.5B Alibaba Qwen	Q8_0	fits	2.2 GB	32k	446tok/sest.	11638 tok/s	chat, coding, long documents
Qwen3.5 0.8B Alibaba Qwen	Q8_0	fits	2.4 GB	256k	338tok/sest.	10932 tok/s	chat, coding, agents, long documents
Qwen3.5 2B Alibaba Qwen	Q5_K_M	fits	3.0 GB	256k	224tok/sest.	5212 tok/s	chat, coding, agents, long documents
DeepSeek R1 Distill Qwen 1.5B DeepSeek	Q8_0	fits	3.9 GB	128k	147tok/sest.	4378 tok/s	chat, coding, long documents
MiniCPM5 2B openbmb	Q8_0	fits	5.1 GB	128k	102tok/sest.	2615 tok/s	chat, coding, agents, long documents
LFM2.5 2.6B Liquid AI	Q8_0	fits	5.8 GB	128k	85tok/sest.	2962 tok/s	chat, coding, agents, long documents
LFM2.5 VL 3B Liquid AI	Q8_0	fits	5.8 GB	32k	85tok/sest.	2716 tok/s	chat, coding, agents, long documents
Mellum2.1 12B A2.5B Thinking JetBrains	Q8_0	fits	13.8 GB	128k	79tok/sest.	3858 tok/s	chat, coding, agents, long documents
granite vision 4.1 4b IBM	Q8_0	fits	7.2 GB	128k	66tok/sest.	1897 tok/s	chat, coding, long documents
granite 4.2 3b IBM	Q8_0	fits	7.4 GB	128k	63tok/sest.	1989 tok/s	chat, coding, agents, long documents
LFM2.5 24B A2B Liquid AI	Q5_K_M	fits	21.0 GB	53k94k with q8 cache	59tok/sest.	2978 tok/s	chat, coding, agents
Kimi VL A3B Moonshot AI	mlx-8bit	fits	18.8 GB	128k	58tok/sest.	2899 tok/s	chat, coding, agents, long documents
DeepSeek R1 Distill Qwen 7B DeepSeek	Q8_0	fits	10.6 GB	128k	42tok/sest.	1279 tok/s	chat, coding, long documents
GLM 4.6V Flash Z.ai	Q8_0	fits	11.9 GB	128k	37tok/sest.	891 tok/s	chat, coding, agents, long documents
DeepSeek R1 Distill Llama 8B DeepSeek	Q8_0	fits	13.2 GB	105k128k with q8 cache	33tok/sest.	1132 tok/s	chat, coding
GLM 4.1V 9B Thinking Z.ai	mlx-8bit	fits	13.5 GB	64k	32tok/sest.	891 tok/s	chat, coding, long documents
Ministral 3 8B Reasoning 2512 Mistral AI	Q8_0	fits	13.9 GB	95k173k with q8 cache	31tok/sest.	1035 tok/s	chat, coding, agents
DeepSeek R1 Distill Qwen 14B DeepSeek	Q8_0	fits	21.9 GB	36k67k with q8 cache	19tok/sest.	611 tok/s	chat
Devstral Small 2507 Mistral AI	Q5_K_M	fits	21.9 GB	37k68k with q8 cache	19tok/sest.	482 tok/s	chat
Magistral Small 2506 Mistral AI	Q5_K_M	fits	21.9 GB	37k40k with q8 cache	19tok/sest.	482 tok/s	chat
Magistral Small 2507 Mistral AI	Q5_K_M	fits	21.9 GB	37k40k with q8 cache	19tok/sest.	482 tok/s	chat
Magistral Small 2509 Mistral AI	Q5_K_M	fits	21.9 GB	37k68k with q8 cache	19tok/sest.	475 tok/s	chat
Qwen 3.5 122B-A10B Alibaba Qwen	UD-Q2_K_XL	offload	41.1 GB	–	14tok/sest.	764 tok/s	chat
Qwen3 Coder Next Alibaba Qwen	Q4_K_M	offload	47.3 GB	–	17tok/sest.	1731 tok/s	chat
Mistral Small 4 119B Mistral AI	UD-Q2_K_XL	offload	39.4 GB	–	20tok/sest.	866 tok/s	chat, coding
Qwen3 Next 80B-A3B Alibaba Qwen	Q4_K_M	offload	47.3 GB	–	20tok/sest.	2059 tok/s	chat, coding
Nemotron 3.5 Lightning 30B-A3B NVIDIA	UD-Q6_K_XL	offload	34.1 GB	–	21tok/sest.	2908 tok/s	chat, coding, long documents
Kimi Linear 48B-A3B Moonshot AI	Q4_K_M	offload	29.6 GB	–	45tok/sest.	2371 tok/s	chat, coding, long documents
Qwen3 32B Alibaba Qwen	Q4_K_M	offload	27.7 GB	12k23k with q8 cache	7tok/sest.	248 tok/s	chat
DeepSeek R1 Distill Qwen 32B DeepSeek	Q4_K_M	offload	27.8 GB	12k23k with q8 cache	7tok/sest.	285 tok/s	chat
granite 4.2 30b IBM	Q4_K_M	offload	26.1 GB	19k35k with q8 cache	8tok/sest.	339 tok/s	chat
DeepSeek V4 Flash DeepSeek	UD-Q2_K_XL	won't run	94.2 GB	–	–	–	–
GLM 5.3 Flash Z.ai	UD-Q2_K_XL	won't run	103.0 GB	–	–	–	–
Qwen 3.8 Flash Next Alibaba Qwen	UD-Q2_K_XL	won't run	75.6 GB	–	–	–	–
MiniMax M2.7 MiniMax	UD-Q2_K_XL	won't run	79.2 GB	–	–	–	–
Nemotron 3 Super 120B-A12B NVIDIA	UD-Q2_K_XL	won't run	52.6 GB	–	–	–	–
gpt-oss 120B OpenAI	Q4_K_M	won't run	60.9 GB	–	–	–	–
GLM 4.5 Air Z.ai	Q2_K	won't run	49.2 GB	–	–	–	–
Llama 3.3 70B Meta	Q4_K_M	won't run	50.9 GB	–	–	–	–
DeepSeek R1 DeepSeek	Q4_K_M	won't run	380.1 GB	–	–	–	–
DeepSeek R1 0528 DeepSeek	Q4_K_M	won't run	380.6 GB	–	–	–	–
DeepSeek R1 Distill Llama 70B DeepSeek	Q4_K_M	won't run	50.9 GB	–	–	–	–
DeepSeek V3 0324 DeepSeek	Q4_K_M	won't run	380.1 GB	–	–	–	–
DeepSeek V3.1 DeepSeek	Q4_K_M	won't run	381.0 GB	–	–	–	–
DeepSeek V3.2 DeepSeek	Q4_K_M	won't run	381.0 GB	–	–	–	–
DeepSeek V4 Flash 0731 DeepSeek	MXFP4	won't run	149.6 GB	–	–	–	–
DeepSeek V4 Flash Vision Exp DeepSeek	MXFP4	won't run	158.4 GB	–	–	–	–
Devstral 2 123B Instruct 2512 Mistral AI	Q8_0	won't run	136.0 GB	–	–	–	–
GLM 4.5V Z.ai	Q4_K_M	won't run	66.3 GB	–	–	–	–
GLM 4.6V Z.ai	Q4_K_M	won't run	72.6 GB	–	–	–	–
GLM 4.7 Z.ai	Q4_K_M	won't run	214.4 GB	–	–	–	–
GLM 5.1 Z.ai	MXFP4	won't run	424.0 GB	–	–	–	–
GLM 5.2 Z.ai	UD-Q4_K_M	won't run	437.9 GB	–	–	–	–
GLM 5.3 Z.ai	Q8_0	won't run	750.4 GB	–	–	–	–
Kimi K2 Moonshot AI	Q4_K_M	won't run	581.6 GB	–	–	–	–
Kimi K2 Instruct 0905 Moonshot AI	Q4_K_M	won't run	582.0 GB	–	–	–	–
Kimi K2 Thinking Moonshot AI	Q4_K_M	won't run	582.0 GB	–	–	–	–
Kimi K2.5 Moonshot AI	Q4_K_M	won't run	582.0 GB	–	–	–	–
MiniMax M2 MiniMax	Q4_K_M	won't run	137.9 GB	–	–	–	–
MiniMax M2.1 MiniMax	Q4_K_M	won't run	137.9 GB	–	–	–	–
MiniMax M2.5 MiniMax	MXFP4	won't run	124.3 GB	–	–	–	–
MiniMax M3 MiniMax	UD-Q4_K_M	won't run	251.8 GB	–	–	–	–
Mistral Medium 3.5 128B Mistral AI	Q4_K_M	won't run	82.0 GB	–	–	–	–

Specifications

From the manufacturer's published specifications; sources are linked where we have them.

GPU: GeForce RTX 5070
Memory: 12 GB GDDR7
Memory bus: 192-bit
Memory bandwidth: 672 GB/s
FP16 compute: 62 TFLOPS
Software: CUDA
Board power: 250 W
PCIe generation: Gen 5
PCIe lanes: x16

Compare with

Questions

How much memory does the NVIDIA GeForce RTX 5070 have for AI models?: The NVIDIA GeForce RTX 5070 has 12 GB of GDDR7 memory with 672 GB/s of bandwidth, which sets how fast it generates text.
What is the best model the NVIDIA GeForce RTX 5070 can run locally?: Qwen 3.8 27B (UD-Q5_K_M) fits fully in its memory at 32k context and generates at about 19 tok/s, an estimate from its memory bandwidth. 48 of the 113 models we track fit at that context.
Can the NVIDIA GeForce RTX 5070 run DeepSeek V4 Flash?: No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 94 GB at 32k context, more than the NVIDIA GeForce RTX 5070 and system RAM can hold.
How much does the NVIDIA GeForce RTX 5070 cost in Germany?: The best new price for the NVIDIA GeForce RTX 5070 in Germany is 699 € at eBay; used, it starts at 780 € (asking price).

Speeds on this page are for 32k context. See the best hardware for local AI at every budget.