Ollama · reflection

During sampling, the model will start by outputting reasoning inside `<thinking>` and `</thinking>` tags, and then once it is satisfied with its reasoning, it will output the final answer inside `<ou…

ollama/reflection

During sampling, the model will start by outputting reasoning inside `<thinking>` and `</thinking>` tags, and then once it is satisfied with its reasoning, it will output the final answer inside `<output>` and `</output>` tags. Each of these tags are special tokens, trained into the model.

This enables the model to separate its internal thoughts and reasoning from its final answer, improving the experience for the user.

Inside the `<thinking>` section, the model may output one or more `<reflection>` tags, which signals the model has caught an error in its reasoning and will attempt to correct it before providing a final answer.

## References

[Hugging Face](https://huggingface.co/mattshumer/ref_70_e3)

Specifications & capabilities

Published model ID
reflection

Deployments & artifacts

1–17 / 17

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q4_0
context window
128000
context window is approximate
true
artifact size bytes
39969818386
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
F16
context window
128000
context window is approximate
true
artifact size bytes
141118127506
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q2_K
context window
128000
context window is approximate
true
artifact size bytes
26375182866
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q3_K_L
context window
128000
context window is approximate
true
artifact size bytes
37140671890
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q3_K_M
context window
128000
context window is approximate
true
artifact size bytes
34267573650
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q3_K_S
context window
128000
context window is approximate
true
artifact size bytes
30912130450
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q4_0
context window
128000
context window is approximate
true
artifact size bytes
39969818386
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q4_1
context window
128000
context window is approximate
true
artifact size bytes
44313678610
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
42520479506
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q4_K_S
context window
128000
context window is approximate
true
artifact size bytes
40347305746
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q5_0
context window
128000
context window is approximate
true
artifact size bytes
48657538834
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q5_1
context window
128000
context window is approximate
true
artifact size bytes
53001399058
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q5_K_M
context window
128000
context window is approximate
true
artifact size bytes
49949908754
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q5_K_S
context window
128000
context window is approximate
true
artifact size bytes
48657538834
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q6_K
context window
128000
context window is approximate
true
artifact size bytes
57888241810
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q8_0
context window
128000
context window is approximate
true
artifact size bytes
74975171986
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q4_0
context window
128000
context window is approximate
true
artifact size bytes
39969818386
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