Back to LeaderboardCompare Hub
Model profile
alpindale

Goliath 120B

Goliath 120B is a mid-range-priced text-first model from alpindale with partial runtime data, compact context posture, and the clearest fit around long-context research.

Best for: Long-context researchN/A latencyCompact contextMid-range pricing
Intelligence
N/A

Benchmark blend

Coding
N/A

Dev workflow signal

Context
6K Tokens

Compact

Input Price
$3.75

Mid-range tier

Decision snapshot
45

Goliath 120B currently reads as a mid-range text-first option with compact context and a partially published runtime profile.

Overall profile
Use-case specific
Best for
Long-context research
Latency tier
N/A
Price tier
Mid-range
Source coverage
OpenRouter
Open compare hubSee leaderboard

Decision Strip

Decision rail before the raw tables

Core buy-side signals stay in one pass. The rest of the page expands only after intelligence, speed, context, and price are clear.

Intelligence
N/A
N/A

General reasoning and benchmark headroom.

Unavailable
Speed
N/A
N/A

Latency data is partial.

Unavailable
Context
6K Tokens
28

How much prompt and task state can stay in view.

Limited
Price
$3.75
62

$7.50 output / 1M

Competitive

Editorial Profile

Goliath 120B in one narrative

Positioning, tradeoffs, and fit are consolidated into one read instead of repeating the same story across separate cards.

Use-case specificCoding score N/AMath score N/A

A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. Credits to - [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge...

Identity

alpindale text-first profile

Positioning

Long-context research with compact context and partially published runtime.

Cost posture

Balanced spend profile. Easier to justify in mixed production and exploration workloads.

Strengths

  • The available source data suggests a balanced profile rather than one dominant edge.

Tradeoffs

  • Costs look manageable, but still deserve attention in always-on agents or batch jobs.

  • Latency data is incomplete, so interactive responsiveness is harder to rank confidently.

  • Current metadata points to a text-first profile rather than a broad multimodal one.

  • Context window is more comfortable for focused tasks than extremely long sessions.

Best fit

  • Focused chat, retrieval-augmented flows, and narrower production tasks.

Benchmarks

Grouped by job-to-be-done

Only benchmark categories with actual signal are shown. Secondary values stay as simple definitions instead of nested micro-cards.

No benchmark data is available for this model yet.

Specs & Pricing

Technical snapshot and cost posture

Specs stay neutral, pricing gets emphasis through values rather than extra containers. Raw provider internals remain in metadata at the end.

Technical snapshot
Context Window
6K Tokens
Vision
Text-first
Modalities
text
Tokenizer
Llama2
Max Completion
1024
Moderation
No
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstoptemperaturetop_atop_ktop_logprobstop_p
Input Modalities
text
Output Modalities
text
Price architecture
Input
per 1M input tokens
$3.75
Output
per 1M output tokens
$7.50
Blended
AA 3:1 mix
N/A

This model sits in a balanced spend range. It is easier to justify across both production and exploratory workflows.

Metadata

Raw source tables at the end

Verification details remain available, but the page no longer forces them ahead of the editorial read.