Your rig

GeForce RTX 4080 Laptop · 12 GB

128 GB system RAM · Ada Lovelace · 432 GB/s · 10.6 GB usable VRAM
Edit hardware Export as JSON

Context length

KV cache at f16, 32K tokens

Quality floor
Q8_0 — near-lossless Q6_K Q5_K_M Q4_K_M — recommended Q3_K_M Q2_K — damaged
KV cache type
System RAM (GB)
Runtime
Ollamallama.cppLM StudiovLLM

4 of 5 runtimes drive this device.

Allow CPU offload Include partial-offload fits

Offloaded layers run at 60 GB/s host bandwidth — expect single-digit tokens per second.

Which one should I actually run?

Best models for your GeForce RTX 4080 Laptop

Updated 8 Oct 2026 1 new this month

What do you want to do? Each row is the best-ranked model on that use case's shortlist that fits at Q2_K and 32K. The ordering is editorial; the sizes and speeds are computed. How the shortlists work.

RecommendationModelWhyQuant · totalTok/s est.
Best overall Gemma 4 12B
Google · Apache 2.0
The 12 GB generalist: text, image and audio in, 140+ languages. Q2_K · 7.6 GB 56 Runs great
Best for coding Qwen3.5 9B
Alibaba · Apache 2.0
The best coding model for 8–12 GB cards. Q2_K · 5.4 GB 69 Runs great
Best reasoning Qwen3.5 9B
Alibaba · Apache 2.0
Thinking mode on a 12 GB card — ahead of the 2025 R1 distills. Q2_K · 5.4 GB 69 Runs great
Best for writing Gemma 4 12B
Google · Apache 2.0
The 12 GB writing pick; 140+ languages. Q2_K · 7.6 GB 56 Runs great
Best vision Gemma 4 12B
Google · Apache 2.0
Image and audio understanding on 12 GB. Q2_K · 7.6 GB 56 Runs great
Best for agents Fara 7B
Microsoft · MIT
Web computer-use only — clicks and fills forms from screenshots, and stops to ask before anything irreversible. Q2_K · 5.6 GB 81 Runs great
Best translation Gemma 4 12B
Google · Apache 2.0
Broad language coverage on a 12 GB card. Q2_K · 7.6 GB 56 Runs great
Fastest good model LFM2.5 8B-A1B
Liquid AI · LFM Open License v1.0
1.5B active; designed for laptops without a GPU. Q2_K · 4.3 GB 172 Runs great
Best long context Qwen3.5 9B
Alibaba · Apache 2.0
262K native in 8–12 GB. Q2_K · 8.4 GB
at 128K context
69 Runs great

Everything that fits

Runs great

30 of 80 · fits with headroom for a longer prompt
ModelParamsQuantWeights +KV 32KTotal VRAM headroom Tok/sRuntime
Gemma 3 12B 12.2B Q2_K 4.8 GB 2.31 GB 7.7 GB
2.9 GB free
55 Ollama Run
Gemma 4 12B 12B Q2_K 4.7 GB 2.31 GB 7.6 GB
3.0 GB free
56 Ollama Run
Qwen3.5 9B 9.65B Q2_K 3.8 GB 1.00 GB 5.4 GB
5.2 GB free
69 Ollama Run
Ornith 1.5 9B 9.41B Q2_K 3.7 GB 1.00 GB 5.3 GB
5.3 GB free
71 Ollama Run
Ministral 3 8B 8.92B Q2_K 3.5 GB 4.25 GB 8.3 GB
2.3 GB free
75 Ollama Run
LFM2.5 8B-A1B 8.47B MoE / 1.5B act Q2_K 3.3 GB 0.38 GB 4.3 GB
6.3 GB free
172 Ollama Run
Fara 7B 8.29B Q2_K 3.2 GB 1.75 GB 5.6 GB
5.0 GB free
81 llama.cpp Run
Qwen3 8B 8.19B Q2_K 3.2 GB 4.50 GB 8.3 GB
2.3 GB free
82 Ollama Run
Llama 3.1 8B Instruct 8.03B Q2_K 3.1 GB 4.00 GB 7.7 GB
2.9 GB free
84 Ollama Run
Gemma 4 E4B 8.0B Q2_K 3.1 GB 0.47 GB 4.2 GB
6.4 GB free
84 Ollama Run
Ling 3.0 Tiny 7.9B-A1.3B 7.9B MoE / 1.3B act Q2_K 3.1 GB 0.21 GB 3.9 GB
6.7 GB free
198 llama.cpp Run
DeepSeek-R1-Distill-Qwen 7B 7.62B Q2_K 3.0 GB 1.75 GB 5.3 GB
5.3 GB free
88 Ollama Run
Qwen2.5-Coder 7B 7.62B Q2_K 3.0 GB 1.75 GB 5.3 GB
5.3 GB free
88 Ollama Run
Olmo 3 7B Instruct 7.3B Q2_K 2.8 GB 5.50 GB 8.9 GB
1.7 GB free
92 Ollama Run
Mistral 7B Instruct v0.3 7.25B Q2_K 2.8 GB 4.00 GB 7.4 GB
3.2 GB free
92 Ollama Run
Gemma 4 E2B 5.1B Q2_K 2.0 GB 0.23 GB 2.8 GB
7.8 GB free
131 Ollama Run
Qwen3.5 4B 4.66B Q2_K 1.8 GB 1.00 GB 3.4 GB
7.2 GB free
144 Ollama Run
Gemma 3 4B 4.3B Q2_K 1.7 GB 0.86 GB 3.1 GB
7.5 GB free
156 Ollama Run
Qwen3 4B 4.02B Q2_K 1.6 GB 4.50 GB 6.7 GB
3.9 GB free
167 Ollama Run
Ministral 3 3B 3.85B Q2_K 1.5 GB 3.25 GB 5.4 GB
5.2 GB free
174 Ollama Run
Phi-4-mini 3.8B 3.84B Q2_K 1.5 GB 4.00 GB 6.1 GB
4.5 GB free
175 Ollama Run
Granite 4.1 3B 3.4B Q2_K 1.3 GB 2.50 GB 4.4 GB
6.2 GB free
197 Ollama Run
Llama 3.2 3B Instruct 3.21B Q2_K 1.3 GB 3.50 GB 5.4 GB
5.2 GB free
209 Ollama Run
LFM2.5 2.6B 2.7B Q2_K 1.1 GB 0.50 GB 2.2 GB
8.4 GB free
248 llama.cpp Run
Qwen3.5 2B 2.27B Q2_K 0.9 GB 0.38 GB 1.9 GB
8.7 GB free
295 Ollama Run
Qwen3 1.7B 1.72B Q2_K 0.7 GB 3.50 GB 4.8 GB
5.8 GB free
390 Ollama Run
Llama 3.2 1B Instruct 1.24B Q2_K 0.5 GB 1.00 GB 2.1 GB
8.5 GB free
541 Ollama Run
Gemma 3 1B 1.0B Q2_K 0.4 GB 0.14 GB 1.1 GB
9.5 GB free
671 Ollama Run
Qwen3.5 0.8B 0.87B Q2_K 0.3 GB 0.38 GB 1.3 GB
9.3 GB free
771 Ollama Run
Qwen3 0.6B 0.6B Q2_K 0.2 GB 3.50 GB 4.3 GB
6.3 GB free
1118 Ollama Run

Runs — tight

3 models · fits at 32K, drop context or quant to go longer
ModelParamsQuantWeights +KV 32KTotal VRAM headroom Tok/sRuntime
Phi-4 14B 14.7B Q2_K 5.7 GB 3.13 GB 9.5 GB
1.1 GB free
46 llama.cpp Run
Mistral NeMo 12B 12.2B Q2_K 4.8 GB 5.00 GB 10.4 GB
0.2 GB free
55 llama.cpp Run
Granite 4.1 8B 8.79B Q2_K 3.4 GB 5.00 GB 9.0 GB
1.6 GB free
76 llama.cpp Run

Won't fit in VRAM

47 models · some are possible with CPU offload
ModelParamsQuantWeights +KV 32KTotal Over budget Tok/sRuntime
DeepSeek V4 Flash 284B-A13B 284B MoE / 13B act Q2_K 110.8 GB 1.51 GB 112.9 GB +102.3 GB ~3.0 llama.cpp Why
Qwen3 235B-A22B 235B MoE / 22B act Q2_K 91.6 GB 5.88 GB 98.1 GB +87.5 GB ~1.7 llama.cpp Why
Qwen3.8-Flash-Next 180B-A6B 180B MoE / 6B act Q2_K 70.2 GB 0.75 GB 71.5 GB +60.9 GB ~6.7 llama.cpp Why
Qwen3.5 122B-A10B 125B MoE / 10B act Q2_K 48.7 GB 0.75 GB 50.1 GB +39.5 GB ~4.3 llama.cpp Why
Nemotron 3 Super 120B-A12B 124B MoE / 12B act Q2_K 48.4 GB 0.25 GB 49.2 GB +38.6 GB ~3.6 llama.cpp Why
Ling 3.0 Flash 124B-A5B 124B MoE / 5.1B act Q2_K 48.4 GB 0.25 GB 49.2 GB +38.6 GB ~8.5 llama.cpp Why
Mistral Small 4 119B-A6B 119B MoE / 6.5B act Q2_K 46.4 GB 0.70 GB 47.7 GB +37.1 GB ~6.7 llama.cpp Why
gpt-oss 120B 117B MoE / 5.1B act MXFP4 60.5 GB 1.13 GB 62.2 GB +51.6 GB ~6.1 llama.cpp Why
Llama 4 Scout 109B-A17B 109B MoE / 17B act Q2_K 42.5 GB 2.63 GB 45.7 GB +35.1 GB ~2.5 llama.cpp Why
Llama 3.3 70B Instruct 70.6B Q2_K 27.5 GB 10.00 GB 38.1 GB +27.5 GB ~1.3 llama.cpp Why
DeepSeek-R1-Distill-Llama 70B 70.6B Q2_K 27.5 GB 10.00 GB 38.1 GB +27.5 GB ~1.3 llama.cpp Why
Qwen3.6 35B-A3B 35.9B MoE / 3.3B act Q2_K 14.0 GB 0.63 GB 15.2 GB +4.6 GB ~26 llama.cpp Why
Ornith 1.5 35B-A3B 35.9B MoE / 3.3B act Q2_K 14.0 GB 0.63 GB 15.2 GB +4.6 GB ~26 llama.cpp Why
LLM-jp 4 33B Thinking 33.2B Q2_K 12.9 GB 8.00 GB 21.5 GB +10.9 GB ~3.2 llama.cpp Why
Qwen3 32B 32.8B Q2_K 12.8 GB 8.00 GB 21.4 GB +10.8 GB ~3.3 llama.cpp Why
DeepSeek-R1-Distill-Qwen 32B 32.8B Q2_K 12.8 GB 8.00 GB 21.4 GB +10.8 GB ~3.3 llama.cpp Why
Qwen2.5-Coder 32B 32.8B Q2_K 12.8 GB 8.00 GB 21.4 GB +10.8 GB ~3.3 llama.cpp Why
Olmo 3.1 32B Instruct 32.2B Q2_K 12.6 GB 2.75 GB 15.9 GB +5.3 GB ~5.8 llama.cpp Why
Nemotron 3.5 Lightning 30B-A3B 31.6B MoE / 3.2B act Q2_K 12.3 GB 0.19 GB 13.1 GB +2.5 GB ~36 llama.cpp Why
Gemma 4 31B 31.3B Q2_K 12.2 GB 5.78 GB 18.6 GB +8.0 GB ~4.2 llama.cpp Why
GLM-4.7-Flash 30B-A3B 31.2B MoE / 3B act Q2_K 12.2 GB 1.65 GB 14.4 GB +3.8 GB ~29 llama.cpp Why
Qwen3 30B-A3B 30.5B MoE / 3.3B act Q2_K 11.9 GB 3.00 GB 15.5 GB +4.9 GB ~22 llama.cpp Why
Qwen3 Coder 30B-A3B 30.5B MoE / 3.3B act Q2_K 11.9 GB 3.00 GB 15.5 GB +4.9 GB ~22 llama.cpp Why
Muse Glimmer 30B 29.8B Q2_K 11.6 GB 0.48 GB 12.7 GB +2.1 GB ~11 llama.cpp Why
Granite 4.1 30B 28.9B Q2_K 11.3 GB 8.00 GB 19.9 GB +9.3 GB ~3.8 llama.cpp Why
Qwen3.8 27B 27.8B Q2_K 10.8 GB 2.00 GB 13.4 GB +2.8 GB ~9.2 llama.cpp Why
Qwen3.6 27B 27.8B Q2_K 10.8 GB 2.00 GB 13.4 GB +2.8 GB ~9.2 llama.cpp Why
Gemma 3 27B 27.4B Q2_K 10.7 GB 2.91 GB 14.2 GB +3.6 GB ~7.9 llama.cpp Why
Gemma 4 26B-A4B 26.5B MoE / 3.8B act Q2_K 10.3 GB 1.45 GB 12.4 GB +1.8 GB ~33 llama.cpp Why
Devstral Small 2 24B 24B Q2_K 9.4 GB 5.00 GB 15.0 GB +4.4 GB ~7.2 llama.cpp Why
Mistral Small 3.2 24B 23.6B Q2_K 9.2 GB 5.00 GB 14.8 GB +4.2 GB ~7.4 llama.cpp Why
gpt-oss 20B 20.9B MoE / 3.6B act MXFP4 10.8 GB 0.75 GB 12.2 GB +1.6 GB ~28 llama.cpp Why
Qwen3 14B 14.8B Q2_K 5.8 GB 5.00 GB 11.4 GB +0.8 GB ~25 llama.cpp Why
DeepSeek-R1-Distill-Qwen 14B 14.8B Q2_K 5.8 GB 6.00 GB 12.4 GB +1.8 GB ~16 llama.cpp Why
Qwen2.5-Coder 14B 14.8B Q2_K 5.8 GB 6.00 GB 12.4 GB +1.8 GB ~16 llama.cpp Why
Ministral 3 14B 13.9B Q2_K 5.4 GB 5.00 GB 11.0 GB +0.4 GB ~33 llama.cpp Why
Kimi K3 2.8T-A104B 2780B MoE / 104B act Q2_K 1084.2 GB 0.84 GB 1085.6 GB +1075.0 GB ~0.3 llama.cpp Why
Qwen3.8 2.4T-A95B 2446B MoE / 95B act Q2_K 953.9 GB 2.88 GB 957.4 GB +946.8 GB ~0.4 llama.cpp Why
DeepSeek V4 Pro 1.6T-A49B 1650B MoE / 49B act Q2_K 643.5 GB 2.14 GB 646.2 GB +635.6 GB ~0.7 llama.cpp Why
Kimi K2.6 1T-A32B 1027B MoE / 32B act Q2_K 400.5 GB 2.14 GB 403.3 GB +392.7 GB ~1.1 llama.cpp Why
GLM-5.2 744B-A40B 753B MoE / 40B act Q2_K 293.7 GB 2.74 GB 297.0 GB +286.4 GB ~0.9 llama.cpp Why
GLM-5.3 744B-A40B 753B MoE / 40B act Q2_K 293.7 GB 2.74 GB 297.0 GB +286.4 GB ~0.9 llama.cpp Why
DeepSeek-R1 671B 671B MoE / 37B act Q2_K 261.7 GB 2.14 GB 264.4 GB +253.8 GB ~1.0 llama.cpp Why
DeepSeek V4.1 Flash 552B-A16B New 552B MoE / 16B act Q2_K 215.3 GB 0.15 GB 216.0 GB +205.4 GB ~2.3 vLLM Why
Qwen3.5 397B-A17B 403B MoE / 17B act Q2_K 157.2 GB 0.94 GB 158.7 GB +148.1 GB ~2.2 llama.cpp Why
Ornith 1.5 397B-A17B 397B MoE / 17B act Q2_K 154.8 GB 0.94 GB 156.4 GB +145.8 GB ~2.2 llama.cpp Why
GLM-5.3-Flash 320B-A18B 321B MoE / 18B act Q2_K 125.2 GB 0.34 GB 126.1 GB +115.5 GB ~2.1 llama.cpp Why

Totals = quantised weights + f16 KV cache at 32K tokens + 0.6 GB runtime overhead, against 10.6 GB usable VRAM (12 GB less display and driver reserve). Tokens per second are estimated from 432 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.


Same memory, different speed

10 of the 12 devices have the same 10.6 GB usable, so they run exactly the models above. Generation speed scales with memory bandwidth.

DeviceBandwidthSpeed vs yours
GeForce RTX 3080 Ti
Ampere · 2021
912 GB/s 2.11×
GeForce RTX 3080 12 GB
Ampere · 2022
912 GB/s 2.11×
GeForce RTX 5070
Blackwell · 2025
672 GB/s 1.56×
GeForce RTX 4070 Ti
Ada Lovelace · 2023
504 GB/s 1.17×
GeForce RTX 4070 Super
Ada Lovelace · 2024
504 GB/s 1.17×
GeForce RTX 4070
Ada Lovelace · 2023
504 GB/s 1.17×
Arc B580
Battlemage · 2024
456 GB/s 1.06×
Radeon RX 7700 XT
RDNA 3 · 2023
432 GB/s same
Radeon RX 6750 XT
RDNA 2 · 2022
432 GB/s same
GeForce RTX 3060 12 GB
Ampere · 2021
360 GB/s 0.83×

Best LLM for 12 GB VRAM, with every card in the class →

What more memory unlocks

At Q4_K_M and 8K context this device fits 37 of 80 models. Each step up, and the largest models it adds:

Every device ranked by what it can run →