← CanIRunLocal · All hardware · All models

Can I run Kev 0.8B (decision) locally?

Kev · 0.8B parameters · chat.

Ollama weight files: Q8_0 0.81 GB (kev:0.8b-q8_0).

Yes on 85 machines in this list. The smallest is M1 8GB: Q8_0, about 1.5 GB, roughly 67 tokens per second, via Ollama. ollama run kev:0.8b-q8_0

DGX Spark 128GB: Q8_0, ~1.5 GB, fits in fast memory, ~253 tok/s — ollama run kev:0.8b-q8_0
Mac Studio M5 Max 128GB: Q8_0, ~1.5 GB, fits in fast memory, ~606 tok/s — ollama run kev:0.8b-q8_0
Mac Studio M5 Ultra 256GB: Q8_0, ~1.5 GB, fits in fast memory, ~1185 tok/s — ollama run kev:0.8b-q8_0

Setup on DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte)

Ollama: ollama run kev:0.8b-q8_0
LM Studio: lms get ggml-org/Kev-0.8B-GGUF@Q8_0
llama.cpp: llama-server -hf ggml-org/Kev-0.8B-GGUF:Q8_0 -c 8192

Open Kev 0.8B (decision) in the checker

Hardware that fits

Hardware	Runtime	Quant	Memory	Fit	Speed	Command
M1 8GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~67 tok/s	`ollama run kev:0.8b-q8_0`
M2 8GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~99 tok/s	`ollama run kev:0.8b-q8_0`
M3 8GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~99 tok/s	`ollama run kev:0.8b-q8_0`
RTX 3060 8GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~178 tok/s	`ollama run kev:0.8b-q8_0`
RTX 3060 Ti 8GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~332 tok/s	`ollama run kev:0.8b-q8_0`
RTX 3070 8GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~332 tok/s	`ollama run kev:0.8b-q8_0`
RTX 4060 8GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~201 tok/s	`ollama run kev:0.8b-q8_0`
RTX 4060 Ti 8GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~213 tok/s	`ollama run kev:0.8b-q8_0`
RX 7600 8GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~213 tok/s	`ollama run kev:0.8b-q8_0`
RTX 3080 10GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~563 tok/s	`ollama run kev:0.8b-q8_0`
M1 16GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~67 tok/s	`ollama run kev:0.8b-q8_0`
M1 Pro 16GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~198 tok/s	`ollama run kev:0.8b-q8_0`
M2 16GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~99 tok/s	`ollama run kev:0.8b-q8_0`
M2 Pro 16GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~198 tok/s	`ollama run kev:0.8b-q8_0`
M3 16GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~99 tok/s	`ollama run kev:0.8b-q8_0`
M4 16GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~119 tok/s	`ollama run kev:0.8b-q8_0`
RTX 3060 12GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~267 tok/s	`ollama run kev:0.8b-q8_0`
RTX 3080 12GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~676 tok/s	`ollama run kev:0.8b-q8_0`
RTX 4070 12GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~373 tok/s	`ollama run kev:0.8b-q8_0`
RTX 5070 12GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~498 tok/s	`ollama run kev:0.8b-q8_0`
M3 Pro 18GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~148 tok/s	`ollama run kev:0.8b-q8_0`
RTX 4060 Ti 16GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~213 tok/s	`ollama run kev:0.8b-q8_0`
RTX 4070 Ti Super 16GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~498 tok/s	`ollama run kev:0.8b-q8_0`
RTX 4080 16GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~531 tok/s	`ollama run kev:0.8b-q8_0`
RTX 5080 16GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~711 tok/s	`ollama run kev:0.8b-q8_0`
RX 7800 XT 16GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~462 tok/s	`ollama run kev:0.8b-q8_0`
RX 9070 XT 16GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~474 tok/s	`ollama run kev:0.8b-q8_0`
M2 24GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~99 tok/s	`ollama run kev:0.8b-q8_0`
M3 24GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~99 tok/s	`ollama run kev:0.8b-q8_0`
M4 24GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~119 tok/s	`ollama run kev:0.8b-q8_0`
M4 Pro 24GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~270 tok/s	`ollama run kev:0.8b-q8_0`
RTX 3090 24GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~693 tok/s	`ollama run kev:0.8b-q8_0`
RTX 4090 24GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~747 tok/s	`ollama run kev:0.8b-q8_0`
RX 7900 XTX 24GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~711 tok/s	`ollama run kev:0.8b-q8_0`
M1 Max (24c GPU) 32GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~395 tok/s	`ollama run kev:0.8b-q8_0`
M1 Max (32c GPU) 32GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~395 tok/s	`ollama run kev:0.8b-q8_0`
M1 Pro 32GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~198 tok/s	`ollama run kev:0.8b-q8_0`
M2 Max (30c GPU) 32GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~395 tok/s	`ollama run kev:0.8b-q8_0`
M2 Max (38c GPU) 32GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~395 tok/s	`ollama run kev:0.8b-q8_0`
M2 Pro 32GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~198 tok/s	`ollama run kev:0.8b-q8_0`
M4 32GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~119 tok/s	`ollama run kev:0.8b-q8_0`
M3 Max (30c GPU) 36GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~296 tok/s	`ollama run kev:0.8b-q8_0`
M3 Pro 36GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~148 tok/s	`ollama run kev:0.8b-q8_0`
M4 Max (32c GPU) 36GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~405 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M4 Max (32c GPU) 36GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~405 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M5 Max (32c GPU) 36GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~454 tok/s	`ollama run kev:0.8b-q8_0`
RTX 5090 32GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~1327 tok/s	`ollama run kev:0.8b-q8_0`
M3 Max (40c GPU) 48GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~395 tok/s	`ollama run kev:0.8b-q8_0`
M4 Max (40c GPU) 48GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~539 tok/s	`ollama run kev:0.8b-q8_0`
M4 Pro 48GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~270 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M4 Max (40c GPU) 48GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~539 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M5 Max (40c GPU) 48GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~606 tok/s	`ollama run kev:0.8b-q8_0`
M1 Max (32c GPU) 64GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~395 tok/s	`ollama run kev:0.8b-q8_0`
M2 Max (30c GPU) 64GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~395 tok/s	`ollama run kev:0.8b-q8_0`
M2 Max (38c GPU) 64GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~395 tok/s	`ollama run kev:0.8b-q8_0`
M2 Ultra 64GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~790 tok/s	`ollama run kev:0.8b-q8_0`
M3 Max (40c GPU) 64GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~395 tok/s	`ollama run kev:0.8b-q8_0`
M4 Max (40c GPU) 64GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~539 tok/s	`ollama run kev:0.8b-q8_0`
M4 Pro 64GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~270 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M4 Max (40c GPU) 64GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~539 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M5 Max (40c GPU) 64GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~606 tok/s	`ollama run kev:0.8b-q8_0`
M2 Max (38c GPU) 96GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~395 tok/s	`ollama run kev:0.8b-q8_0`
M3 Max (30c GPU) 96GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~296 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M3 Ultra (60c GPU) 96GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~809 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M3 Ultra (80c GPU) 96GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~809 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M5 Ultra (64c GPU) 96GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~1185 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M5 Ultra (80c GPU) 96GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~1185 tok/s	`ollama run kev:0.8b-q8_0`
M2 Ultra 128GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~790 tok/s	`ollama run kev:0.8b-q8_0`
M3 Max (40c GPU) 128GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~395 tok/s	`ollama run kev:0.8b-q8_0`
M4 Max (40c GPU) 128GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~539 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M4 Max (40c GPU) 128GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~539 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M5 Max (40c GPU) 128GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~606 tok/s	`ollama run kev:0.8b-q8_0`
DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte)	Ollama	Q8_0	1.5 GB	fits in fast memory	~253 tok/s	`ollama run kev:0.8b-q8_0`
M2 Ultra 192GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~790 tok/s	`ollama run kev:0.8b-q8_0`
2x Mac Studio M5 Max (40c GPU) 128GB	llama.cpp	Q8_0 GGUF	1.5 GB	fits in fast memory	~515 tok/s	`llama-server -hf ggml-org/Kev-0.8B-GGUF:Q8_0 --rpc node2:50052 -c 8192 # run rpc-server on each other node`
Mac Studio M3 Ultra (60c GPU) 256GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~809 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M3 Ultra (80c GPU) 256GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~809 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M5 Ultra (64c GPU) 256GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~1185 tok/s	`ollama run kev:0.8b-q8_0`
Mac Studio M5 Ultra (80c GPU) 256GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~1185 tok/s	`ollama run kev:0.8b-q8_0`
2x DGX Spark 128GB	llama.cpp	Q8_0 GGUF	1.5 GB	fits in fast memory	~215 tok/s	`llama-server -hf ggml-org/Kev-0.8B-GGUF:Q8_0 --rpc node2:50052 -c 8192 # run rpc-server on each other node`
4x Mac Studio M5 Max (40c GPU) 128GB	llama.cpp	Q8_0 GGUF	1.5 GB	fits in fast memory	~455 tok/s	`llama-server -hf ggml-org/Kev-0.8B-GGUF:Q8_0 --rpc node2:50052,node3:50052,node4:50052 -c 8192 # run rpc-server on each other node`
2x Mac Studio M5 Ultra (80c GPU) 256GB	llama.cpp	Q8_0 GGUF	1.5 GB	fits in fast memory	~1007 tok/s	`llama-server -hf ggml-org/Kev-0.8B-GGUF:Q8_0 --rpc node2:50052 -c 8192 # run rpc-server on each other node`
Mac Studio M3 Ultra (80c GPU) 512GB	Ollama	Q8_0	1.5 GB	fits in fast memory	~809 tok/s	`ollama run kev:0.8b-q8_0`
4x DGX Spark 128GB	llama.cpp	Q8_0 GGUF	1.5 GB	fits in fast memory	~190 tok/s	`llama-server -hf ggml-org/Kev-0.8B-GGUF:Q8_0 --rpc node2:50052,node3:50052,node4:50052 -c 8192 # run rpc-server on each other node`
4x Mac Studio M5 Ultra (80c GPU) 256GB	llama.cpp	Q8_0 GGUF	1.5 GB	fits in fast memory	~889 tok/s	`llama-server -hf ggml-org/Kev-0.8B-GGUF:Q8_0 --rpc node2:50052,node3:50052,node4:50052 -c 8192 # run rpc-server on each other node`

Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-19.

A project by OnDevice Labs · llms.txt