Vertical Tabs
Get Started
Sao10k

Llama 3 8B Lunaris

Structured output
Hugging Face
Llama 3 8B Lunaris model card cover
Context
8K
Released
2y ago
Parameters
8B
Input / 1M tokens
$0.04
Output / 1M tokens
$0.05

Sources:OpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer
Sao10k
Model family
—
Type
Language model
Predecessor
—
Successor
—
Released
June 26, 2024
Model ID
sao10k/l3-lunaris-8b
Openness
Open weights
License
—
Parameters
8B
Input modalities
text
Output modalities
text
Modality
text->text
Native context
8K
Tokenizer
Llama3
Max output tokens
7K
Knowledge cutoff
2023-12-31
Hugging Face
Sao10K/L3-8B-Lunaris-v1
Source freshness
Endpoints synced Oct 15, 2026, 10:17 AM UTC

Open-weight builds

Ollama variants

Every published Ollama tag matched to this model, including parameter editions, instruction/base variants, and quantized builds.

60 builds
VariantParametersTypeQuantizationSizeContextInput
llama3:8b-instruct-fp168BinstructFP1616 GB8Ktext
llama3:8b-instruct-q2_K8BinstructQ2_K3.2 GB8Ktext
llama3:8b-instruct-q3_K_L8BinstructQ3_K_L4.3 GB8Ktext
llama3:8b-instruct-q3_K_M8BinstructQ3_K_M4 GB8Ktext
llama3:8b-instruct-q3_K_S8BinstructQ3_K_S3.7 GB8Ktext
llama3:latest8BinstructQ4_04.7 GB8Ktext
llama3:8b-instruct-q4_18BinstructQ4_15.1 GB8Ktext
llama3:8b-instruct-q4_K_M8BinstructQ4_K_M4.9 GB8Ktext
llama3:8b-instruct-q4_K_S8BinstructQ4_K_S4.7 GB8Ktext
llama3:8b-instruct-q5_08BinstructQ5_05.6 GB8Ktext
llama3:8b-instruct-q5_18BinstructQ5_16.1 GB8Ktext
llama3:8b-instruct-q5_K_M8BinstructQ5_K_M5.7 GB8Ktext
llama3:8b-instruct-q5_K_S8BinstructQ5_K_S5.6 GB8Ktext
llama3:8b-instruct-q6_K8BinstructQ6_K6.6 GB8Ktext
llama3:8b-instruct-q8_08BinstructQ8_08.5 GB8Ktext
llama3:8b-text-fp168BtextFP1616 GB8Ktext
llama3:8b-text-q2_K8BtextQ2_K3.2 GB8Ktext
llama3:8b-text-q3_K_L8BtextQ3_K_L4.3 GB8Ktext
llama3:8b-text-q3_K_M8BtextQ3_K_M4 GB8Ktext
llama3:8b-text-q3_K_S8BtextQ3_K_S3.7 GB8Ktext
llama3:8b-text8BtextQ4_04.7 GB8Ktext
llama3:8b-text-q4_18BtextQ4_15.1 GB8Ktext
llama3:8b-text-q4_K_M8BtextQ4_K_M4.9 GB8Ktext
llama3:8b-text-q4_K_S8BtextQ4_K_S4.7 GB8Ktext
llama3:8b-text-q5_08BtextQ5_05.6 GB8Ktext
llama3:8b-text-q5_18BtextQ5_16.1 GB8Ktext
llama3:8b-text-q5_K_M8BtextQ5_K_M5.7 GB8Ktext
llama3:8b-text-q5_K_S8BtextQ5_K_S5.6 GB8Ktext
llama3:8b-text-q6_K8BtextQ6_K6.6 GB8Ktext
llama3:8b-text-q8_08BtextQ8_08.5 GB8Ktext
llama3:70b-instruct-fp1670BinstructFP16141 GB8Ktext
llama3:70b-instruct-q2_K70BinstructQ2_K26 GB8Ktext
llama3:70b-instruct-q3_K_L70BinstructQ3_K_L37 GB8Ktext
llama3:70b-instruct-q3_K_M70BinstructQ3_K_M34 GB8Ktext
llama3:70b-instruct-q3_K_S70BinstructQ3_K_S31 GB8Ktext
llama3:70b70BinstructQ4_040 GB8Ktext
llama3:70b-instruct-q4_170BinstructQ4_144 GB8Ktext
llama3:70b-instruct-q4_K_M70BinstructQ4_K_M43 GB8Ktext
llama3:70b-instruct-q4_K_S70BinstructQ4_K_S40 GB8Ktext
llama3:70b-instruct-q5_070BinstructQ5_049 GB8Ktext
llama3:70b-instruct-q5_170BinstructQ5_153 GB8Ktext
llama3:70b-instruct-q5_K_M70BinstructQ5_K_M50 GB8Ktext
llama3:70b-instruct-q5_K_S70BinstructQ5_K_S49 GB8Ktext
llama3:70b-instruct-q6_K70BinstructQ6_K58 GB8Ktext
llama3:70b-instruct-q8_070BinstructQ8_075 GB8Ktext
llama3:70b-text-fp1670BtextFP16141 GB8Ktext
llama3:70b-text-q2_K70BtextQ2_K26 GB8Ktext
llama3:70b-text-q3_K_L70BtextQ3_K_L37 GB8Ktext
llama3:70b-text-q3_K_M70BtextQ3_K_M34 GB8Ktext
llama3:70b-text-q3_K_S70BtextQ3_K_S31 GB8Ktext
llama3:70b-text70BtextQ4_040 GB8Ktext
llama3:70b-text-q4_170BtextQ4_144 GB8Ktext
llama3:70b-text-q4_K_M70BtextQ4_K_M43 GB8Ktext
llama3:70b-text-q4_K_S70BtextQ4_K_S40 GB8Ktext
llama3:70b-text-q5_070BtextQ5_049 GB8Ktext
llama3:70b-text-q5_170BtextQ5_153 GB8Ktext
llama3:70b-text-q5_K_M70BtextQ5_K_M50 GB8Ktext
llama3:70b-text-q5_K_S70BtextQ5_K_S49 GB8Ktext
llama3:70b-text-q6_K70BtextQ6_K58 GB8Ktext
llama3:70b-text-q8_070BtextQ8_075 GB8Ktext

Infrastructure

Provider availability

All providers
ProviderEndpointContextInput /M tokensOutput /M tokensCached input /M tokensCache write /M tokensUptime 1dData handling
DeepInfradeepinfra/turbo8K$0.04$0.05——100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

ZDR source Privacy policy

Checked 2026-10-15

Parasailparasail/bf168K$0.04$0.05——100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

ZDR source Privacy policy

Checked 2026-10-15

Provider data:OpenRouter

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware