Best local LLMs for long context

Run open models featuring a context window of at least 128K tokens to handle large documents and full codebases easily. We rank them using the llmrun Composite Score, highlighting our top recommendation for every memory capacity.

Best for long context on

8 GB 12 GB 16 GB 24 GB 32 GB 48 GB+

Top pick

DeepSeek V4.1 Flash 1017

DeepSeek · Q4_K_M · needs 458 GB · up to 1M context · runs on about 7× H100 SXM 80 GB · from $18.83/hr in the cloudDeepSeek · Q4_K_M · needs 458 GB · runs on about 7× H100 SXM 80 GB · from $18.83/hr in the cloud

No memory limit: the best model, whatever memory it needs.

Score
Context: up to 1M context

How to run →

All 178 long-context models, no memory limit ↓

Also worth a look

MiMo V2.6 Pro RL

Q4_K_M · needs 614 GB · about 5× H200 SXM 141 GB · 1M ctx

Kimi K3

Q4_K_M · needs 1.7 TB · about 3 nodes of 8× H100 SXM 80 GB · 1M ctx

Also worth a look

MiMo V2.6 Pro RL

Q4_K_M · needs 614 GB · about 5× H200 SXM 141 GB · 1M ctx

Best long-context model by memory

Highest llmrun Composite Score that fits each size with at least 128K context and 10 t/s, at a Q3 or better quant. Speed is decode tokens per second on that size's reference GPU. The last row has no memory limit: the best model whatever it needs, on the GPU plan shown. Full ranking

8 GB · RTX 5060
Gemma 4 E4B IT58.0 t/s · 128K ctx
Q4_K_S · 5.3 GB
Runner-up: Ling 3.0 Tiny
12 GB · RTX 5070
Qwen3.5 9B68.7 t/s · 128K ctx
Q4_K_M · 6.6 GB
Runner-up: GPT OSS 20B
16 GB · RTX 5080
Gemma 4 26B A4B IT207.5 t/s · 128K ctx
IQ3_S · 12 GB
Runner-up: Qwen3.5 9B
24 GB · RTX 4090
Qwen3.8 27B40.0 t/s · 128K ctx
Q4_K_S · 16.8 GB
Runner-up: Gemma 4 26B A4B IT
32 GB · RTX 5090
Qwen3.8 27B66.9 t/s · 256K ctx
Q4_K_M · 17.9 GB
Runner-up: Gemma 4 31B IT
48 GB+ · no limit · about 7× H100 SXM 80 GB
DeepSeek V4.1 Flash 10171M ctx
Q4_K_M · needs 458 GB
Runner-up: MiMo V2.6 Pro RL

Best long-context model for each memory size
Memory	Best pick	Score	Speed	Context (fits)	Runner-up
8 GBRTX 5060	Gemma 4 E4B ITQ4_K_S · 5.3 GB	n/a	58.0 t/s	128K	Ling 3.0 Tiny243.0 t/s
12 GBRTX 5070	Qwen3.5 9BQ4_K_M · 6.6 GB		68.7 t/s	128K	GPT OSS 20B96.4 · 172.1 t/s
16 GBRTX 5080	Gemma 4 26B A4B ITIQ3_S · 12 GB		207.5 t/s	128K	Qwen3.5 9B99.4 · 98.1 t/s
24 GBRTX 4090	Qwen3.8 27BQ4_K_S · 16.8 GB		40.0 t/s	128K	Gemma 4 26B A4B IT105.8 · 171.1 t/s
32 GBRTX 5090	Qwen3.8 27BQ4_K_M · 17.9 GB		66.9 t/s	256K	Gemma 4 31B IT106.6 · 74.2 t/s
48 GB+ · no limitabout 7× H100 SXM 80 GB	DeepSeek V4.1 Flash 1017Q4_K_M · needs 458 GB		n/a	1M	MiMo V2.6 Pro RL133.2

Long-context models, no memory limit178

Ranked by Composite Score, models without one after. Memory is what the listed quant needs; speed is shown only for models that fit one 48 GB GPU.

178 models

Featured only

Score: llmrun Score, 100 = average model. Ordered by Score. How ranking works

LLM models ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context
Qwen3.5 0.8B873MVisionFunctions Q4_K_M·717.2 t/s	Q4_K_M	0.9 GB	717.2 t/s	262K
Youtu Parsing Omni5.3BVision BF16·55.8 t/s	BF16	12.7 GB	55.8 t/s	1049K
EXAONE 4.5 33B34.4BVisionFunctions Q4_K_M·29.1 t/s	Q4_K_M	25.2 GB	29.1 t/s	262K
Kimi VL A3B Instruct16.4BVisionFunctions Q4_K_M·201.4 t/s	Q4_K_M	10.7 GB	201.4 t/s	131K
Agnes 3.0 Flash33.1BVisionReasoningFunctions Q4_K_M·30.2 t/s	Q4_K_M	24.2 GB	30.2 t/s	262K
MiniCPM5 1B1.1BChatFunctions Q4_K_M·630.3 t/s	Q4_K_M	1.3 GB	630.3 t/s	131K
Granite Switch 4.1 30B30.0BChatFunctions Q4_K_M·33.1 t/s	Q4_K_M	22.7 GB	33.1 t/s	131K
Qwen3 VL 8B Instruct8.8BVisionFunctions Q4_K_M·106.5 t/s	Q4_K_M	8.0 GB	106.5 t/s	262K
Apriel 1.6 15B Thinker14.9BVisionFunctions Q4_K_M·64.2 t/s	Q4_K_M	13.2 GB	64.2 t/s	262K
Qwen3 VL 4B Instruct4.4BVisionFunctions Q4_K_M·198.1 t/s	Q4_K_M	4.5 GB	198.1 t/s	262K
Llama 3.2 3B Instruct3.2BChatFunctions Q4_K_M·294.3 t/s	Q4_K_M	4.1 GB	294.3 t/s	131K
Falcon H1 7B Instruct7.6BChatFunctions Q4_K_M·123.8 t/s	Q4_K_M	6.3 GB	123.8 t/s	262K
Granite 4.0 H Small32.2BChatFunctions Q4_K_M·91.4 t/s	Q4_K_M	22.3 GB	91.4 t/s	131K
Qwen3 VL 32B Instruct33.4BVisionFunctions Q4_K_M·30.2 t/s	Q4_K_M	23 GB	30.2 t/s	262K
Qwen3 Next 80B A3B Thinking81.3BChatFunctions Q4_K_S·130.5 t/s	Q4_K_S	46.3 GB	130.5 t/s	262K

How much memory do you need for long context?

On 8 GB the best long-context model is Gemma 4 E4B IT. At 12 GB it is Qwen3.5 9B (score 99). At 16 GB it is Gemma 4 26B A4B IT (score 106). From 24 to 32 GB it is Qwen3.8 27B (score 122). With no memory limit, the best is DeepSeek V4.1 Flash 1017 (score 133). Weights cover just part of the cost. As tokens fill the cache in your window, a complete 128K prompt may require several gigabytes beyond the model itself. The listed sizes allow space for up to a 16K context.

Frequently Asked Questions

What is the best local LLM for long context?

On 24 GB, Qwen3.8 27B is the top pick with a score of 122, running at about 40 t/s on RTX 4090. It fits up to 128K tokens of context there. On 8 GB, the best fit is Gemma 4 E4B IT. With no memory limit, the best is DeepSeek V4.1 Flash 1017. Open a model to see which GPUs and Macs run it.

Does a long context window use more memory?

The key-value cache scales linearly as token count rises, reaching sizes that can match the model's weights around 128K tokens. Techniques like cache quantization or using grouped-query attention can shrink this footprint.

Is a bigger context window always better?

Quality for info buried deep in a long prompt often slips, plus handling a lengthy request eats up time. Stick to the length you actually need instead of maxing it out.