Ollama · falcon3

<img src="https://ollama.com/assets/library/falcon3/7ead93c7-c315-42ad-b49f-3aa370c3e7db" width="425" /> Falcon3 represents TII's latest advancement in efficient language models under 10B parameters,…

ollama/falcon3

<img src="https://ollama.com/assets/library/falcon3/7ead93c7-c315-42ad-b49f-3aa370c3e7db" width="425" />

Falcon3 represents TII's latest advancement in efficient language models under 10B parameters, focused on enhancing science, math, and code capabilities while maintaining training efficiency.

# Key Features - Four sizes: 1B, 3B, 7B, 10B - Depth up-scaling technique used to create 10B model from 7B - Knowledge distillation for smaller models (1B, 3B)

# Performance Highlights - `falcon3:1b` outperforms `smollm2:1.7b`, matches `gemma2:2b` - `falcon3:10b` achieves SOTA in under-13B category - Extended context length up to 32K tokens (8K for 1B model)

# References [Hugging Face](https://huggingface.co/blog/falcon3)

Specifications & capabilities

Published model ID
falcon3

Deployments & artifacts

1–17 / 17

ollama

source id
ollama
execution mode
local
parameter size
10.3B
parameter count
10300000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
32000
context window is approximate
true
artifact size bytes
6287533530
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
10.3B
parameter count
10300000000
parameter count is approximate
true
quantization level
F16
context window
32000
context window is approximate
true
artifact size bytes
20616570330
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
10.3B
parameter count
10300000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
32000
context window is approximate
true
artifact size bytes
6287533530
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
10.3B
parameter count
10300000000
parameter count is approximate
true
quantization level
Q8_0
context window
32000
context window is approximate
true
artifact size bytes
10955253210
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
1.7B
parameter count
1700000000
parameter count is approximate
true
quantization level
Q8_0
context window
8000
context window is approximate
true
artifact size bytes
1778722778
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
1.7B
parameter count
1700000000
parameter count is approximate
true
quantization level
F16
context window
8000
context window is approximate
true
artifact size bytes
3343722458
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
1.7B
parameter count
1700000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
8000
context window is approximate
true
artifact size bytes
1057056730
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
1.7B
parameter count
1700000000
parameter count is approximate
true
quantization level
Q8_0
context window
8000
context window is approximate
true
artifact size bytes
1778722778
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.2B
parameter count
3200000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
32000
context window is approximate
true
artifact size bytes
2005696570
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.2B
parameter count
3200000000
parameter count is approximate
true
quantization level
F16
context window
32000
context window is approximate
true
artifact size bytes
6460342330
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.2B
parameter count
3200000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
32000
context window is approximate
true
artifact size bytes
2005696570
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.2B
parameter count
3200000000
parameter count is approximate
true
quantization level
Q8_0
context window
32000
context window is approximate
true
artifact size bytes
3434545210
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
7.5B
parameter count
7500000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
32000
context window is approximate
true
artifact size bytes
4569738490
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
7.5B
parameter count
7500000000
parameter count is approximate
true
quantization level
F16
context window
32000
context window is approximate
true
artifact size bytes
14916209914
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
7.5B
parameter count
7500000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
32000
context window is approximate
true
artifact size bytes
4569738490
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
7.5B
parameter count
7500000000
parameter count is approximate
true
quantization level
Q8_0
context window
32000
context window is approximate
true
artifact size bytes
7926795514
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
7.5B
parameter count
7500000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
32000
context window is approximate
true
artifact size bytes
4569738490
updated at
2026-11-16T08:10:06.079865+00:00

Original sources

1–2 / 2

Ollama · Model page ↗

Ollama · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace