NVIDIA · Blackwell

What runs on a RTX 5070 Ti

16 GB at 896 GB/s. The largest model that fits at Q4_K_M is gpt-oss 20B-A3.6B, at roughly 185 tokens per second.

Model

Hardware

Quantisation

Context 8K

KV cache precision

Runtime

Batch

GPUs

Monitor plugged into this GPU

Runs comfortably

6.4 GB of 14.2 GB · 45%

014 GB

Weights 4.6 GB

KV cache 1.0 GB

Runtime overhead 0.8 GB

Llama 3.1 8B at Q4_K_M leaves 7.8 GB spare on a RTX 5070 Ti. There is room to raise the context length or move up a quantisation level.

Generation113tok/s

Prompt processing2301tok/s

Max context70Ktokens

KV per 1K tokens0GB

Every quantisation of Llama 3.1 8B on a RTX 5070 Ti

Highlighted row is the highest quality that still fits at 8K context.

Quantisation	bpw	Weights	Total	Verdict	Max ctx	tok/s
FP16 / BF16	16.00	15.0 GB	16.8 GB	Won't fit	—	11.1
INT8 / W8A8	8.50	7.7 GB	9.5 GB	Runs comfortably	46K	71.2
Q8_0 (GGUF)	8.50	7.7 GB	9.5 GB	Runs comfortably	46K	71.2
FP8 (E4M3)	8.00	7.5 GB	9.3 GB	Runs comfortably	48K	73.2
Q6_K	6.56	6.1 GB	8.0 GB	Runs comfortably	58K	87.8
AWQ 4-bit	4.25	5.4 GB	7.2 GB	Runs comfortably	64K	98.3
GPTQ 4-bit	4.25	5.4 GB	7.2 GB	Runs comfortably	64K	98.3
MXFP4	4.25	5.4 GB	7.2 GB	Runs comfortably	64K	98.3
Q5_K_M	5.67	5.3 GB	7.1 GB	Runs comfortably	65K	100
Q5_K_S	5.52	5.2 GB	7.0 GB	Runs comfortably	66K	103
Q4_K_M	4.85	4.6 GB	6.4 GB	Runs comfortably	70K	113
Q4_K_S	4.58	4.4 GB	6.2 GB	Runs comfortably	72K	118
Q4_0	4.55	4.4 GB	6.2 GB	Runs comfortably	72K	119
IQ4_XS	4.25	4.1 GB	5.9 GB	Runs comfortably	74K	125
Q3_K_M	3.91	3.8 GB	5.7 GB	Runs comfortably	77K	133
IQ3_M	3.70	3.7 GB	5.5 GB	Runs comfortably	78K	138
IQ3_XXS	3.06	3.2 GB	5.0 GB	Runs comfortably	82K	157
Q2_K	2.63	2.8 GB	4.6 GB	Runs comfortably	85K	173
IQ2_XXS	2.06	2.3 GB	4.2 GB	Runs comfortably	89K	200
IQ1_M	1.75	2.1 GB	3.9 GB	Runs comfortably	91K	219

Q4_K_M at 8K context. Bandwidth sets the speed; capacity sets the ceiling.

Model	Params	Weights	Verdict	Max ctx	tok/s
DeepSeek-R1 671B-A37B	671B	379.0 GB	Won't fit	—	2.03
Qwen3 235B-A22B	235.1B	132.8 GB	Won't fit	—	3.36
gpt-oss 120B-A5.1B	116.8B	66.0 GB	Won't fit	—	15.8
Llama 4 Scout 109B-A17B	109B	61.7 GB	Won't fit	—	4.90
Qwen2.5 72B	72.7B	41.2 GB	Won't fit	—	1.31
Llama 3.1 70B	70.5B	40.0 GB	Won't fit	—	1.35
Mixtral 8x7B	46.7B	26.4 GB	Won't fit	—	9.44
Command R 35B	35.0B	20.1 GB	Won't fit	—	1.95
Yi-1.5 34B	34.4B	19.5 GB	Won't fit	—	4.50
Qwen3 32B	32.8B	18.6 GB	Won't fit	—	4.95
Qwen2.5-Coder 32B	32.8B	18.6 GB	Won't fit	—	4.95
DeepSeek-R1-Distill-Qwen 32B	32.8B	18.6 GB	Won't fit	—	4.95
Qwen3 30B-A3B	30.5B	17.3 GB	Won't fit	—	45.7
Gemma 3 27B	27.4B	15.6 GB	Won't fit	—	9.17
Mistral Small 24B	23.6B	13.4 GB	Won't fit	—	18.2
gpt-oss 20B-A3.6B	20.9B	11.9 GB	Fits, but tight	33K	185
Qwen3 14B	14.8B	8.5 GB	Runs comfortably	32K	64.2
Phi-4 14B	14.7B	8.4 GB	Runs comfortably	16K	63.7
Mistral NeMo 12B	12.3B	7.0 GB	Runs comfortably	41K	76.1
Gemma 3 12B	12.2B	7.0 GB	Runs comfortably	98K	76.9
GLM-4 9B	9.4B	5.4 GB	Runs comfortably	128K	104
Qwen3 8B	8.2B	4.7 GB	Runs comfortably	62K	109
Llama 3.1 8B	8.0B	4.6 GB	Runs comfortably	70K	113
DeepSeek-R1-Distill-Llama 8B	8.0B	4.6 GB	Runs comfortably	70K	113
Qwen2.5 7B	7.6B	4.4 GB	Runs comfortably	128K	126
Mistral 7B v0.3	7.3B	4.1 GB	Runs comfortably	32K	125
Gemma 3 4B	4.3B	2.5 GB	Runs comfortably	128K	211
Qwen3 4B	4.0B	2.3 GB	Runs comfortably	79K	198
Llama 3.2 3B	3.2B	1.8 GB	Runs comfortably	106K	249
Llama 3.2 1B	1.2B	0.7 GB	Runs comfortably	128K	657