llmrun

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 GB12 GB16 GB24 GB32 GB48 GB+

Qwen3.8 27B

Alibaba · Q4_K_M · 17.9 GB · up to 256K context · on RTX 5090

66.9 t/s
S
How to run →

All 96 long-context models for 32 GB ↓

Also worth a look

Gemma 4 31B IT

IQ3_M · 17 GB · 74.2 t/s · 128K 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

Long-context models that run on 32 GB96

Ranked by Composite Score, models without one after. Best quant that fits with a 16K context; speed is decode tokens per second on the reference GPU.

96 models · 86 run great · 10 run well

Featured only

Score: llmrun Score, 100 = average model. Fit: how well it runs on this hardware, S best to F won't fit. Ordered by Score, recency and Fit. How ranking works

Showing compatibility for NVIDIA GeForce RTX 5090

LLM models compatible with NVIDIA GeForce RTX 5090 — ranked by Score, recency and Fit
ModelVRAMScoreFit
Qwen3.5 9B Base
Q4_K_M·183.1 t/s
6.6 GBS99, Runs great
Qwen3 VL 8B Thinking
Q4_K_M·198.8 t/s
8.0 GBS100, Runs great
Phi 3.5 MoE Instruct
< 128K context fits
Q4_K_M·190.2 t/s
27.6 GBS92, Runs great
Qwen3 VL 2B Thinking
Q4_K_M·643.5 t/s
3.5 GBS100, Runs great
Gemma 4 26B A4B
Q4_K_M·249.5 t/s
16.5 GBS100, Runs great
Qwen3.5 0.8B Base
Q4_K_M·1338.9 t/s
0.9 GBS100, Runs great
Gemma 4 12B
Q4_K_M·141.5 t/s
9.0 GBS96, Runs great
Qwen3.5 2B Base
Q4_K_M·658.1 t/s
1.9 GBS100, Runs great
Qwen3 VL 4B Thinking
Q4_K_M·369.8 t/s
4.5 GBS100, Runs great
Gemma 4 E2B
Q4_K_M·339.6 t/s
3.5 GBS100, Runs great
Granite 4.0 Micro
Q4_K_M·464.1 t/s
3.7 GBS100, Runs great
DeepSeek R1 Distill Qwen 7B
Q4_K_M·233.4 t/s
5.8 GBS100, Runs great
Seed OSS 36B Base
< 128K context fits
Q4_K_M·52.3 t/s
24.1 GBA81, Runs well
Phi 4 Mini Instruct
Q4_K_M·405.9 t/s
4.8 GBS100, Runs great
Phi 4 Mini Reasoning
Q4_K_M·405.9 t/s
4.8 GBS100, Runs great

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.